def classifier_multiclasslogisticregression_modular(
fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
label_test_multiclass=label_testdat,
z=1,
epsilon=1e-5):
from modshogun import RealFeatures, MulticlassLabels
try:
from modshogun import MulticlassLogisticRegression
except ImportError:
print("recompile shogun with Eigen3 support")
return
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = MulticlassLogisticRegression(z, feats_train, labels)
classifier.train()
label_pred = classifier.apply(feats_test)
out = label_pred.get_labels()
if label_test_multiclass is not None:
from modshogun 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_relaxedtree(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 modshogun import RealFeatures, MulticlassLabels
from modshogun import RelaxedTree, MulticlassLibLinear
from modshogun import GaussianKernel
#print('Working on a problem of %d features and %d samples' % fm_train_real.shape)
feats_train = RealFeatures(fm_train_real)
labels = MulticlassLabels(label_train_multiclass)
machine = RelaxedTree()
machine.set_machine_for_confusion_matrix(MulticlassLibLinear())
machine.set_kernel(GaussianKernel())
machine.set_labels(labels)
machine.train(feats_train)
label_pred = machine.apply_multiclass(RealFeatures(fm_test_real))
out = label_pred.get_labels()
if label_test_multiclass is not None:
from modshogun 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_relaxedtree (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 modshogun import RealFeatures, MulticlassLabels
from modshogun import RelaxedTree, MulticlassLibLinear
from modshogun import GaussianKernel
#print('Working on a problem of %d features and %d samples' % fm_train_real.shape)
feats_train = RealFeatures(fm_train_real)
labels = MulticlassLabels(label_train_multiclass)
machine = RelaxedTree()
machine.set_machine_for_confusion_matrix(MulticlassLibLinear())
machine.set_kernel(GaussianKernel())
machine.set_labels(labels)
machine.train(feats_train)
label_pred = machine.apply_multiclass(RealFeatures(fm_test_real))
out = label_pred.get_labels()
if label_test_multiclass is not None:
from modshogun 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_multiclasslogisticregression_modular(
fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
label_test_multiclass=label_testdat,
z=1,
epsilon=1e-5,
):
from modshogun import RealFeatures, MulticlassLabels
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = MulticlassLogisticRegression(z, feats_train, labels)
classifier.train()
label_pred = classifier.apply(feats_test)
out = label_pred.get_labels()
if label_test_multiclass is not None:
from modshogun 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_discriminant (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 modshogun import RealFeatures, MulticlassLabels
from modshogun import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from modshogun 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 modshogun 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_shareboost (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 modshogun import RealFeatures, RealSubsetFeatures, MulticlassLabels
from modshogun import ShareBoost
#print('Working on a problem of %d features and %d samples' % fm_train_real.shape)
feats_train = RealFeatures(fm_train_real)
labels = MulticlassLabels(label_train_multiclass)
shareboost = ShareBoost(feats_train, labels, min(fm_train_real.shape[0]-1, 30))
shareboost.train();
#print(shareboost.get_activeset())
feats_test = RealSubsetFeatures(RealFeatures(fm_test_real), shareboost.get_activeset())
label_pred = shareboost.apply(feats_test)
out = label_pred.get_labels()
if label_test_multiclass is not None:
from modshogun 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_multiclassliblinear_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 modshogun import RealFeatures, MulticlassLabels
from modshogun import MulticlassLibLinear
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = MulticlassLibLinear(C, feats_train, labels)
classifier.train()
label_pred = classifier.apply(feats_test)
out = label_pred.get_labels()
if label_test_multiclass is not None:
from modshogun 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,
label_test_multiclass=label_testdat,
width=2.1,
C=1,
epsilon=1e-5):
from modshogun import RealFeatures, MulticlassLabels
from modshogun 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 modshogun 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,label_test_multiclass=label_testdat,width=2.1,C=1,epsilon=1e-5):
from modshogun import RealFeatures, MulticlassLabels
from modshogun 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 modshogun import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(label_pred, labels_test)
print('Accuracy = %.4f' % acc)
return out
def shareboost(train_features, train_labels, test_features, test_labels): from modshogun import ShareBoost, MulticlassAccuracy, RealSubsetFeatures shareboost = ShareBoost(train_features, train_labels, min(train_features.get_num_features()-1, 30)) shareboost.train() feats_test = RealSubsetFeatures(test_features, shareboost.get_activeset()) test_output = shareboost.apply(feats_test) evaluator = MulticlassAccuracy() print 'ShareBoost test error is %.4f' % ((1-evaluator.evaluate(test_output, test_labels))*100)
def qda(train_features, train_labels, test_featues, test_labels): from modshogun import QDA, MulticlassAccuracy qda = QDA(train_features, train_labels) qda.train() train_output = qda.apply() test_output = qda.apply(test_features) evaluator = MulticlassAccuracy() print 'QDA training error is %.4f' % ((1-evaluator.evaluate(train_output, train_labels))*100) print 'QDA test error is %.4f' % ((1-evaluator.evaluate(test_output, test_labels))*100)
def evaluation_multiclassaccuracy_modular (ground_truth, predicted): from modshogun import MulticlassLabels from modshogun import MulticlassAccuracy ground_truth_labels = MulticlassLabels(ground_truth) predicted_labels = MulticlassLabels(predicted) evaluator = MulticlassAccuracy() accuracy = evaluator.evaluate(predicted_labels,ground_truth_labels) return accuracy
def evaluation_multiclassaccuracy_modular(ground_truth, predicted):
from modshogun import MulticlassLabels
from modshogun import MulticlassAccuracy
ground_truth_labels = MulticlassLabels(ground_truth)
predicted_labels = MulticlassLabels(predicted)
evaluator = MulticlassAccuracy()
accuracy = evaluator.evaluate(predicted_labels, ground_truth_labels)
return accuracy
def knn(train_features, train_labels, test_features, test_labels, k=1): from modshogun import KNN, MulticlassAccuracy, EuclideanDistance distance = EuclideanDistance(train_features, train_features) knn = KNN(k, distance, train_labels) knn.train() train_output = knn.apply() test_output = knn.apply(test_features) evaluator = MulticlassAccuracy() print 'KNN training error is %.4f' % ((1-evaluator.evaluate(train_output, train_labels))*100) print 'KNN test error is %.4f' % ((1-evaluator.evaluate(test_output, test_labels))*100)
def evaluate4svm(labels, feats, params={'c': 1, 'kernal': 'gauss'}, Nsplit=2):
"""
Run Cross-validation to evaluate the SVM.
Parameters
----------
labels: 2d array
Data set labels.
feats: array
Data set feats.
params: dictionary
Search scope parameters.
Nsplit: int, default = 2
The n for n-fold cross validation.
"""
c = params.get('c')
if params.get('kernal' == 'gauss'):
kernal = GaussianKernel()
kernal.set_width(80)
elif params.get('kernal' == 'sigmoid'):
kernal = SigmoidKernel()
else:
kernal = LinearKernel()
split = CrossValidationSplitting(labels, Nsplit)
split.build_subsets()
accuracy = np.zeros(Nsplit)
time_test = np.zeros(accuracy.shape)
for i in range(Nsplit):
idx_train = split.generate_subset_inverse(i)
idx_test = split.generate_subset_indices(i)
feats.add_subset(idx_train)
labels.add_subset(idx_train)
print c, kernal, labels
svm = GMNPSVM(c, kernal, labels)
_ = svm.train(feats)
out = svm.apply(feats_test)
evaluator = MulticlassAccuracy()
accuracy[i] = evaluator.evaluate(out, labels_test)
feats.remove_subset()
labels.remove_subset()
feats.add_subset(idx_test)
labels.add_subset(idx_test)
t_start = time.clock()
time_test[i] = (time.clock() - t_start) / labels.get_num_labels()
feats.remove_subset()
labels.remove_subset()
return accuracy
def shareboost(train_features, train_labels, test_features, test_labels):
from modshogun import ShareBoost, MulticlassAccuracy, RealSubsetFeatures
shareboost = ShareBoost(train_features, train_labels,
min(train_features.get_num_features() - 1, 30))
shareboost.train()
feats_test = RealSubsetFeatures(test_features, shareboost.get_activeset())
test_output = shareboost.apply(feats_test)
evaluator = MulticlassAccuracy()
print 'ShareBoost test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
def knn(train_features, train_labels, test_features, test_labels, k=1):
from modshogun import KNN, MulticlassAccuracy, EuclideanDistance
distance = EuclideanDistance(train_features, train_features)
knn = KNN(k, distance, train_labels)
knn.train()
train_output = knn.apply()
test_output = knn.apply(test_features)
evaluator = MulticlassAccuracy()
print 'KNN training error is %.4f' % (
(1 - evaluator.evaluate(train_output, train_labels)) * 100)
print 'KNN test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
def qda(train_features, train_labels, test_featues, test_labels):
from modshogun import QDA, MulticlassAccuracy
qda = QDA(train_features, train_labels)
qda.train()
train_output = qda.apply()
test_output = qda.apply(test_features)
evaluator = MulticlassAccuracy()
print 'QDA training error is %.4f' % (
(1 - evaluator.evaluate(train_output, train_labels)) * 100)
print 'QDA test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
def mkl(train_features,
train_labels,
test_features,
test_labels,
width=5,
C=1.2,
epsilon=1e-2,
mkl_epsilon=0.001,
mkl_norm=2):
from modshogun import CombinedKernel, CombinedFeatures
from modshogun import GaussianKernel, LinearKernel, PolyKernel
from modshogun import MKLMulticlass, MulticlassAccuracy
kernel = CombinedKernel()
feats_train = CombinedFeatures()
feats_test = CombinedFeatures()
feats_train.append_feature_obj(train_features)
feats_test.append_feature_obj(test_features)
subkernel = GaussianKernel(10, width)
kernel.append_kernel(subkernel)
feats_train.append_feature_obj(train_features)
feats_test.append_feature_obj(test_features)
subkernel = LinearKernel()
kernel.append_kernel(subkernel)
feats_train.append_feature_obj(train_features)
feats_test.append_feature_obj(test_features)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_train)
mkl = MKLMulticlass(C, kernel, train_labels)
mkl.set_epsilon(epsilon)
mkl.set_mkl_epsilon(mkl_epsilon)
mkl.set_mkl_norm(mkl_norm)
mkl.train()
train_output = mkl.apply()
kernel.init(feats_train, feats_test)
test_output = mkl.apply()
evaluator = MulticlassAccuracy()
print 'MKL training error is %.4f' % (
(1 - evaluator.evaluate(train_output, train_labels)) * 100)
print 'MKL test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
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 modshogun import RealFeatures, MulticlassLabels
from modshogun import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from modshogun import ECOCStrategy, ECOCRandomSparseEncoder, ECOCRandomDenseEncoder, ECOCHDDecoder
from modshogun import Math_init_random
Math_init_random(12345)
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 modshogun 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_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 modshogun import RealFeatures, MulticlassLabels
from modshogun import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from modshogun 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 modshogun 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 knn_classify(traindat, testdat, k=3): from modshogun import KNN, MulticlassAccuracy, EuclideanDistance train_features, train_labels = traindat.features, traindat.labels distance = EuclideanDistance(train_features, train_features) knn = KNN(k, distance, train_labels) knn.train() test_features, test_labels = testdat.features, testdat.labels predicted_labels = knn.apply(test_features) evaluator = MulticlassAccuracy() acc = evaluator.evaluate(predicted_labels, test_labels) err = 1-acc return err
def knn_classify(traindat, testdat, k=3):
from modshogun import KNN, MulticlassAccuracy, EuclideanDistance
train_features, train_labels = traindat.features, traindat.labels
distance = EuclideanDistance(train_features, train_features)
knn = KNN(k, distance, train_labels)
knn.train()
test_features, test_labels = testdat.features, testdat.labels
predicted_labels = knn.apply(test_features)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(predicted_labels, test_labels)
err = 1 - acc
return err
def lmnn_diagonal(train_features, train_labels, test_features, test_labels, k=1): from modshogun import LMNN, KNN, MSG_DEBUG, MulticlassAccuracy import numpy lmnn = LMNN(train_features, train_labels, k) lmnn.set_diagonal(True) lmnn.train() distance = lmnn.get_distance() knn = KNN(k, distance, train_labels) knn.train() train_output = knn.apply() test_output = knn.apply(test_features) evaluator = MulticlassAccuracy() print 'LMNN-diagonal training error is %.4f' % ((1-evaluator.evaluate(train_output, train_labels))*100) print 'LMNN-diagonal test error is %.4f' % ((1-evaluator.evaluate(test_output, test_labels))*100)
def main(actual, predicted):
LOGGER.info("SVM Multiclass evaluator")
# Load SVMLight dataset
feats, labels = get_features_and_labels(LibSVMFile(actual))
# Load predicted labels
with open(predicted, 'r') as f:
predicted_labels_arr = np.array([float(l) for l in f])
predicted_labels = MulticlassLabels(predicted_labels_arr)
# Evaluate accuracy
multiclass_measures = MulticlassAccuracy()
LOGGER.info("Accuracy = %s" % multiclass_measures.evaluate(
labels, predicted_labels))
LOGGER.info("Confusion matrix:")
res = multiclass_measures.get_confusion_matrix(labels, predicted_labels)
print res
def lmnn(train_features, train_labels, test_features, test_labels, k=1): from modshogun import LMNN, KNN, MSG_DEBUG, MulticlassAccuracy import numpy # dummy = LMNN() # dummy.io.set_loglevel(MSG_DEBUG) lmnn = LMNN(train_features, train_labels, k) lmnn.train() distance = lmnn.get_distance() knn = KNN(k, distance, train_labels) knn.train() train_output = knn.apply() test_output = knn.apply(test_features) evaluator = MulticlassAccuracy() print 'LMNN training error is %.4f' % ((1-evaluator.evaluate(train_output, train_labels))*100) print 'LMNN test error is %.4f' % ((1-evaluator.evaluate(test_output, test_labels))*100)
def classifier_multiclass_ecoc_discriminant(
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 modshogun import RealFeatures, MulticlassLabels
from modshogun import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from modshogun 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 modshogun import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(label_pred, labels_test)
print('Accuracy = %.4f' % acc)
return out
def run_ecoc(ier, idr): encoder = getattr(modshogun, encoders[ier])() decoder = getattr(modshogun, decoders[idr])() # whether encoder is data dependent if hasattr(encoder, 'set_labels'): encoder.set_labels(gnd_train) encoder.set_features(fea_train) strategy = ECOCStrategy(encoder, decoder) classifier = LinearMulticlassMachine(strategy, fea_train, base_classifier, gnd_train) classifier.train() label_pred = classifier.apply(fea_test) if gnd_test is not None: evaluator = MulticlassAccuracy() acc = evaluator.evaluate(label_pred, gnd_test) else: acc = None return (classifier.get_num_machines(), acc)
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 modshogun import RealFeatures, MulticlassLabels
from modshogun import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from modshogun 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 modshogun 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 run_ecoc(ier, idr):
encoder = getattr(Classifier, encoders[ier])()
decoder = getattr(Classifier, decoders[idr])()
# whether encoder is data dependent
if hasattr(encoder, 'set_labels'):
encoder.set_labels(gnd_train)
encoder.set_features(fea_train)
strategy = ECOCStrategy(encoder, decoder)
classifier = LinearMulticlassMachine(strategy, fea_train,
base_classifier, gnd_train)
classifier.train()
label_pred = classifier.apply(fea_test)
if gnd_test is not None:
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(label_pred, gnd_test)
else:
acc = None
return (classifier.get_num_machines(), acc)
def lmnn(train_features, train_labels, test_features, test_labels, k=1):
from modshogun import LMNN, KNN, MSG_DEBUG, MulticlassAccuracy
import numpy
# dummy = LMNN()
# dummy.io.set_loglevel(MSG_DEBUG)
lmnn = LMNN(train_features, train_labels, k)
lmnn.train()
distance = lmnn.get_distance()
knn = KNN(k, distance, train_labels)
knn.train()
train_output = knn.apply()
test_output = knn.apply(test_features)
evaluator = MulticlassAccuracy()
print 'LMNN training error is %.4f' % (
(1 - evaluator.evaluate(train_output, train_labels)) * 100)
print 'LMNN test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
def mkl(train_features, train_labels, test_features, test_labels, width=5, C=1.2, epsilon=1e-2, mkl_epsilon=0.001, mkl_norm=2): from modshogun import CombinedKernel, CombinedFeatures from modshogun import GaussianKernel, LinearKernel, PolyKernel from modshogun import MKLMulticlass, MulticlassAccuracy kernel = CombinedKernel() feats_train = CombinedFeatures() feats_test = CombinedFeatures() feats_train.append_feature_obj(train_features) feats_test.append_feature_obj(test_features) subkernel = GaussianKernel(10,width) kernel.append_kernel(subkernel) feats_train.append_feature_obj(train_features) feats_test.append_feature_obj(test_features) subkernel = LinearKernel() kernel.append_kernel(subkernel) feats_train.append_feature_obj(train_features) feats_test.append_feature_obj(test_features) subkernel = PolyKernel(10,2) kernel.append_kernel(subkernel) kernel.init(feats_train, feats_train) mkl = MKLMulticlass(C, kernel, train_labels) mkl.set_epsilon(epsilon); mkl.set_mkl_epsilon(mkl_epsilon) mkl.set_mkl_norm(mkl_norm) mkl.train() train_output = mkl.apply() kernel.init(feats_train, feats_test) test_output = mkl.apply() evaluator = MulticlassAccuracy() print 'MKL training error is %.4f' % ((1-evaluator.evaluate(train_output, train_labels))*100) print 'MKL test error is %.4f' % ((1-evaluator.evaluate(test_output, test_labels))*100)
def lmnn_classify(traindat, testdat, k=3): from modshogun import LMNN, KNN, MulticlassAccuracy, MSG_DEBUG train_features, train_labels = traindat.features, traindat.labels lmnn = LMNN(train_features, train_labels, k) lmnn.set_maxiter(1200) lmnn.io.set_loglevel(MSG_DEBUG) lmnn.train() distance = lmnn.get_distance() knn = KNN(k, distance, train_labels) knn.train() test_features, test_labels = testdat.features, testdat.labels predicted_labels = knn.apply(test_features) evaluator = MulticlassAccuracy() acc = evaluator.evaluate(predicted_labels, test_labels) err = 1-acc return err
def lmnn_classify(traindat, testdat, k=3):
from modshogun import LMNN, KNN, MulticlassAccuracy, MSG_DEBUG
train_features, train_labels = traindat.features, traindat.labels
lmnn = LMNN(train_features, train_labels, k)
lmnn.set_maxiter(1200)
lmnn.io.set_loglevel(MSG_DEBUG)
lmnn.train()
distance = lmnn.get_distance()
knn = KNN(k, distance, train_labels)
knn.train()
test_features, test_labels = testdat.features, testdat.labels
predicted_labels = knn.apply(test_features)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(predicted_labels, test_labels)
err = 1 - acc
return err
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 modshogun import RealFeatures, MulticlassLabels
from modshogun import LibLinear, L2R_L2LOSS_SVC, LinearMulticlassMachine
from modshogun import ECOCStrategy, ECOCRandomSparseEncoder, ECOCRandomDenseEncoder, ECOCHDDecoder
from modshogun import Math_init_random;
Math_init_random(12345);
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 modshogun 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_multiclassliblinear_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 modshogun import RealFeatures, MulticlassLabels
from modshogun import MulticlassLibLinear
feats_train=RealFeatures(fm_train_real)
feats_test=RealFeatures(fm_test_real)
labels=MulticlassLabels(label_train_multiclass)
classifier = MulticlassLibLinear(C,feats_train,labels)
classifier.train()
label_pred = classifier.apply(feats_test)
out = label_pred.get_labels()
if label_test_multiclass is not None:
from modshogun import MulticlassAccuracy
labels_test = MulticlassLabels(label_test_multiclass)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(label_pred, labels_test)
print('Accuracy = %.4f' % acc)
return out
def lmnn_diagonal(train_features,
train_labels,
test_features,
test_labels,
k=1):
from modshogun import LMNN, KNN, MSG_DEBUG, MulticlassAccuracy
import numpy
lmnn = LMNN(train_features, train_labels, k)
lmnn.set_diagonal(True)
lmnn.train()
distance = lmnn.get_distance()
knn = KNN(k, distance, train_labels)
knn.train()
train_output = knn.apply()
test_output = knn.apply(test_features)
evaluator = MulticlassAccuracy()
print 'LMNN-diagonal training error is %.4f' % (
(1 - evaluator.evaluate(train_output, train_labels)) * 100)
print 'LMNN-diagonal test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
def evaluate(labels,
feats,
params={
'n_neighbors': 2,
'use_cover_tree': 'True',
'dist': 'Manhattan'
},
Nsplit=2):
"""
Run Cross-validation to evaluate the KNN.
Parameters
----------
labels: 2d array
Data set labels.
feats: array
Data set feats.
params: dictionary
Search scope parameters.
Nsplit: int, default = 2
The n for n-fold cross validation.
all_ks: range of int, default = range(1, 21)
Numbers of neighbors.
"""
k = params.get('n_neighbors')
use_cover_tree = params.get('use_cover_tree') == 'True'
if params.get('dist' == 'Euclidean'):
func_dist = EuclideanDistance
else:
func_dist = ManhattanMetric
split = CrossValidationSplitting(labels, Nsplit)
split.build_subsets()
accuracy = np.zeros(Nsplit)
acc_train = np.zeros(accuracy.shape)
time_test = np.zeros(accuracy.shape)
for i in range(Nsplit):
idx_train = split.generate_subset_inverse(i)
idx_test = split.generate_subset_indices(i)
feats.add_subset(idx_train)
labels.add_subset(idx_train)
dist = func_dist(feats, feats)
knn = KNN(k, dist, labels)
knn.set_store_model_features(True)
if use_cover_tree:
knn.set_knn_solver_type(KNN_COVER_TREE)
else:
knn.set_knn_solver_type(KNN_BRUTE)
knn.train()
evaluator = MulticlassAccuracy()
pred = knn.apply_multiclass()
acc_train[i] = evaluator.evaluate(pred, labels)
feats.remove_subset()
labels.remove_subset()
feats.add_subset(idx_test)
labels.add_subset(idx_test)
t_start = time.clock()
pred = knn.apply_multiclass(feats)
time_test[i] = (time.clock() - t_start) / labels.get_num_labels()
accuracy[i] = evaluator.evaluate(pred, labels)
feats.remove_subset()
labels.remove_subset()
print accuracy.mean()
return accuracy
def evaluation_cross_validation_multiclass_storage (traindat=traindat, label_traindat=label_traindat):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import CrossValidationPrintOutput
from modshogun import CrossValidationMKLStorage, CrossValidationMulticlassStorage
from modshogun import MulticlassAccuracy, F1Measure
from modshogun import StratifiedCrossValidationSplitting
from modshogun import MulticlassLabels
from modshogun import RealFeatures, CombinedFeatures
from modshogun import GaussianKernel, CombinedKernel
from modshogun import MKLMulticlass
from modshogun import Statistics, MSG_DEBUG, Math
Math.init_random(1)
# training data, combined features all on same data
features=RealFeatures(traindat)
comb_features=CombinedFeatures()
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
labels=MulticlassLabels(label_traindat)
# kernel, different Gaussians combined
kernel=CombinedKernel()
kernel.append_kernel(GaussianKernel(10, 0.1))
kernel.append_kernel(GaussianKernel(10, 1))
kernel.append_kernel(GaussianKernel(10, 2))
# create mkl using libsvm, due to a mem-bug, interleaved is not possible
svm=MKLMulticlass(1.0,kernel,labels);
svm.set_kernel(kernel);
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy=StratifiedCrossValidationSplitting(labels, 3)
# evaluation method
evaluation_criterium=MulticlassAccuracy()
# cross-validation instance
cross_validation=CrossValidation(svm, comb_features, labels,
splitting_strategy, evaluation_criterium)
cross_validation.set_autolock(False)
# append cross vlaidation output classes
#cross_validation.add_cross_validation_output(CrossValidationPrintOutput())
#mkl_storage=CrossValidationMKLStorage()
#cross_validation.add_cross_validation_output(mkl_storage)
multiclass_storage=CrossValidationMulticlassStorage()
multiclass_storage.append_binary_evaluation(F1Measure())
cross_validation.add_cross_validation_output(multiclass_storage)
cross_validation.set_num_runs(3)
# perform cross-validation
result=cross_validation.evaluate()
roc_0_0_0 = multiclass_storage.get_fold_ROC(0,0,0)
#print roc_0_0_0
auc_0_0_0 = multiclass_storage.get_fold_evaluation_result(0,0,0,0)
#print auc_0_0_0
return roc_0_0_0, auc_0_0_0