def kernel_director_linear_modular(fm_train_real=traindat,
fm_test_real=testdat,
scale=1.2):
from shogun.Kernel import LinearKernel, AvgDiagKernelNormalizer
from modshogun import Time
feats_train = RealFeatures(fm_train_real)
feats_train.io.set_loglevel(0)
feats_train.parallel.set_num_threads(1)
feats_test = RealFeatures(fm_test_real)
kernel = LinearKernel()
kernel.set_normalizer(AvgDiagKernelNormalizer(scale))
kernel.init(feats_train, feats_train)
dkernel = DirectorLinearKernel()
dkernel.set_normalizer(AvgDiagKernelNormalizer(scale))
dkernel.init(feats_train, feats_train)
print "km_train"
t = Time()
km_train = kernel.get_kernel_matrix()
t1 = t.cur_time_diff(True)
print "dkm_train"
t = Time()
dkm_train = dkernel.get_kernel_matrix()
t2 = t.cur_time_diff(True)
print "km_train", km_train
print "dkm_train", dkm_train
return km_train, dkm_train
def create_kernel(kname, kparam, feats_train):
"""Call the corresponding constructor for the kernel"""
if kname == 'gauss':
kernel = GaussianKernel(feats_train, feats_train, kparam['width'])
elif kname == 'linear':
kernel = LinearKernel(feats_train, feats_train)
kernel.set_normalizer(AvgDiagKernelNormalizer(kparam['scale']))
elif kname == 'poly':
kernel = PolyKernel(feats_train, feats_train, kparam['degree'],
kparam['inhomogene'], kparam['normal'])
elif kname == 'wd':
kernel = WeightedDegreePositionStringKernel(feats_train, feats_train,
kparam['degree'])
kernel.set_normalizer(
AvgDiagKernelNormalizer(float(kparam['seqlength'])))
kernel.set_shifts(kparam['shift'] *
numpy.ones(kparam['seqlength'], dtype=numpy.int32))
#kernel=WeightedDegreeStringKernel(feats_train, feats_train, kparam['degree'])
elif kname == 'spec':
kernel = CommUlongStringKernel(feats_train, feats_train)
elif kname == 'cumspec':
kernel = WeightedCommWordStringKernel(feats_train, feats_train)
kernel.set_weights(numpy.ones(kparam['degree']))
elif kname == 'spec2':
kernel = CombinedKernel()
k0 = CommWordStringKernel(feats_train['f0'], feats_train['f0'])
k0.io.disable_progress()
kernel.append_kernel(k0)
k1 = CommWordStringKernel(feats_train['f1'], feats_train['f1'])
k1.io.disable_progress()
kernel.append_kernel(k1)
elif kname == 'cumspec2':
kernel = CombinedKernel()
k0 = WeightedCommWordStringKernel(feats_train['f0'], feats_train['f0'])
k0.set_weights(numpy.ones(kparam['degree']))
k0.io.disable_progress()
kernel.append_kernel(k0)
k1 = WeightedCommWordStringKernel(feats_train['f1'], feats_train['f1'])
k1.set_weights(numpy.ones(kparam['degree']))
k1.io.disable_progress()
kernel.append_kernel(k1)
elif kname == 'localalign':
kernel = LocalAlignmentStringKernel(feats_train, feats_train)
elif kname == 'localimprove':
kernel = LocalityImprovedStringKernel(feats_train, feats_train, kparam['length'],\
kparam['indeg'], kparam['outdeg'])
else:
print 'Unknown kernel %s' % kname
kernel.set_cache_size(32)
return kernel
def kernel_director_linear_modular(fm_train_real=traindat,
fm_test_real=testdat,
scale=1.2):
try:
from shogun.Kernel import DirectorKernel
except ImportError:
print "recompile shogun with --enable-swig-directors"
return
class DirectorLinearKernel(DirectorKernel):
def __init__(self):
DirectorKernel.__init__(self, True)
def kernel_function(self, idx_a, idx_b):
seq1 = self.get_lhs().get_feature_vector(idx_a)
seq2 = self.get_rhs().get_feature_vector(idx_b)
return numpy.dot(seq1, seq2)
from shogun.Kernel import LinearKernel, AvgDiagKernelNormalizer
from modshogun import Time
feats_train = RealFeatures(fm_train_real)
#feats_train.io.set_loglevel(MSG_DEBUG)
feats_train.parallel.set_num_threads(1)
feats_test = RealFeatures(fm_test_real)
kernel = LinearKernel()
kernel.set_normalizer(AvgDiagKernelNormalizer(scale))
kernel.init(feats_train, feats_train)
dkernel = DirectorLinearKernel()
dkernel.set_normalizer(AvgDiagKernelNormalizer(scale))
dkernel.init(feats_train, feats_train)
#print "km_train"
t = Time()
km_train = kernel.get_kernel_matrix()
#t1=t.cur_time_diff(True)
#print "dkm_train"
t = Time()
dkm_train = dkernel.get_kernel_matrix()
#t2=t.cur_time_diff(True)
#print "km_train", km_train
#print "dkm_train", dkm_train
return km_train, dkm_train
def kernel_match_word_string_modular(fm_train_dna=traindat,
fm_test_dna=testdat,
degree=3,
scale=1.4,
size_cache=10,
order=3,
gap=0,
reverse=False):
from shogun.Kernel import MatchWordStringKernel, AvgDiagKernelNormalizer
from shogun.Features import StringWordFeatures, StringCharFeatures, DNA
charfeat = StringCharFeatures(fm_train_dna, DNA)
feats_train = StringWordFeatures(DNA)
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
charfeat = StringCharFeatures(fm_test_dna, DNA)
feats_test = StringWordFeatures(DNA)
feats_test.obtain_from_char(charfeat, order - 1, order, gap, reverse)
kernel = MatchWordStringKernel(size_cache, degree)
kernel.set_normalizer(AvgDiagKernelNormalizer(scale))
kernel.init(feats_train, feats_train)
km_train = kernel.get_kernel_matrix()
kernel.init(feats_train, feats_test)
km_test = kernel.get_kernel_matrix()
return km_train, km_test, kernel
def kernel_sparse_linear_modular (fm_train_real=traindat,fm_test_real=testdat,scale=1.1): from shogun.Features import SparseRealFeatures from shogun.Kernel import LinearKernel, AvgDiagKernelNormalizer feats_train=SparseRealFeatures(fm_train_real) feats_test=SparseRealFeatures(fm_test_real) kernel=LinearKernel() kernel.set_normalizer(AvgDiagKernelNormalizer(scale)) kernel.init(feats_train, feats_train) km_train=kernel.get_kernel_matrix() kernel.init(feats_train, feats_test) km_test=kernel.get_kernel_matrix() return km_train,km_test,kernel
def kernel_linear_word_modular (fm_train_word=traindat,fm_test_word=testdat,scale=1.2): from shogun.Kernel import LinearKernel, AvgDiagKernelNormalizer from shogun.Features import WordFeatures feats_train=WordFeatures(fm_train_word) feats_test=WordFeatures(fm_test_word) kernel=LinearKernel(feats_train, feats_train) kernel.set_normalizer(AvgDiagKernelNormalizer(scale)) kernel.init(feats_train, feats_train) km_train=kernel.get_kernel_matrix() kernel.init(feats_train, feats_test) km_test=kernel.get_kernel_matrix() return kernel
