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_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.Library 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.classify().get_labels() predictions = svm.classify() return predictions, svm, predictions.get_labels()
alpha = old_svm.get_alpha(j)
inner_sum = inner_sum + alpha * kv.kernel(sv_id, idx)
inner.append(inner_sum)
#general case
linterm_manual[idx] = B * tmp_lab[idx] * inner_sum - 1.0
################
# compare pre-svms
assert (presvm_liblinear.get_bias() == 0.0)
assert (presvm_libsvm.get_bias() == 0.0)
tmp_out = presvm_liblinear.classify(feat).get_labels()
tmp_out2 = presvm_libsvm.classify(feat).get_labels()
# compare outputs
for i in xrange(N):
try:
assert (abs(inner[i] - tmp_out[i]) <= 0.001)
assert (abs(inner[i] - tmp_out2[i]) <= 0.001)
except Exception, message:
print "difference in outputs: (%.4f, %.4f, %.4f)" % (tmp_out[i],
tmp_out2[i])
###############
# compare to LibSVM
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
inner_sum = inner_sum + alpha * kv.kernel(sv_id, idx)
inner.append(inner_sum)
#general case
linterm_manual[idx] = B *tmp_lab[idx] * inner_sum - 1.0
################
# compare pre-svms
assert(presvm_liblinear.get_bias() == 0.0)
assert(presvm_libsvm.get_bias() == 0.0)
tmp_out = presvm_liblinear.classify(feat).get_labels()
tmp_out2 = presvm_libsvm.classify(feat).get_labels()
# compare outputs
for i in xrange(N):
try:
assert(abs(inner[i]-tmp_out[i])<= 0.001)
assert(abs(inner[i]-tmp_out2[i])<= 0.001)
except Exception, message:
print "difference in outputs: (%.4f, %.4f, %.4f)" % (tmp_out[i], tmp_out2[i])
###############
