def comm_ulong_string (): print 'CommUlongString' from shogun.Kernel import CommUlongStringKernel from shogun.Features import StringUlongFeatures, StringCharFeatures, DNA from shogun.PreProc import SortUlongString order=3 gap=0 reverse=False charfeat=StringCharFeatures(DNA) charfeat.set_features(fm_train_dna) feats_train=StringUlongFeatures(charfeat.get_alphabet()) feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse) preproc=SortUlongString() preproc.init(feats_train) feats_train.add_preproc(preproc) feats_train.apply_preproc() charfeat=StringCharFeatures(DNA) charfeat.set_features(fm_test_dna) feats_test=StringUlongFeatures(charfeat.get_alphabet()) feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse) feats_test.add_preproc(preproc) feats_test.apply_preproc() use_sign=False kernel=CommUlongStringKernel(feats_train, feats_train, use_sign) km_train=kernel.get_kernel_matrix() kernel.init(feats_train, feats_test) km_test=kernel.get_kernel_matrix()
def preprocessor_sortulongstring_modular (fm_train_dna=traindna,fm_test_dna=testdna,order=3,gap=0,reverse=False,use_sign=False): from shogun.Kernel import CommUlongStringKernel from shogun.Features import StringCharFeatures, StringUlongFeatures, DNA from shogun.Preprocessor import SortUlongString charfeat=StringCharFeatures(DNA) charfeat.set_features(fm_train_dna) feats_train=StringUlongFeatures(charfeat.get_alphabet()) feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse) charfeat=StringCharFeatures(DNA) charfeat.set_features(fm_test_dna) feats_test=StringUlongFeatures(charfeat.get_alphabet()) feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse) preproc=SortUlongString() preproc.init(feats_train) feats_train.add_preprocessor(preproc) feats_train.apply_preprocessor() feats_test.add_preprocessor(preproc) feats_test.apply_preprocessor() kernel=CommUlongStringKernel(feats_train, feats_train, use_sign) 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 get_kernel_matrix(li):
"""
Get kernel matrix from a list of strings.
"""
order = 6
gap = 2
reverse = False
charfeat = StringCharFeatures(RAWBYTE)
charfeat.set_features(li)
#Get alphabet.
feats_train = StringUlongFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
#CommUlongStringKernel needs sorted features.
preproc = SortUlongString()
preproc.init(feats_train)
feats_train.add_preproc(preproc)
feats_train.apply_preproc()
use_sign = False
#Compute kernel matrix between train features.
kernel = CommUlongStringKernel(feats_train, feats_train, use_sign)
km_train = kernel.get_kernel_matrix()
return km_train
def get_kernel_matrix(li):
"""
Get kernel matrix from a list of strings.
"""
order = 6
gap = 2
reverse = False
charfeat = StringCharFeatures(RAWBYTE)
charfeat.set_features(li)
#Get alphabet.
feats_train = StringUlongFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
#CommUlongStringKernel needs sorted features.
preproc = SortUlongString()
preproc.init(feats_train)
feats_train.add_preproc(preproc)
feats_train.apply_preproc()
use_sign = False
#Compute kernel matrix between train features.
kernel = CommUlongStringKernel(feats_train, feats_train, use_sign)
km_train = kernel.get_kernel_matrix()
return km_train
def kernel_comm_ulong_string_modular(fm_train_dna=traindat,
fm_test_dna=testdat,
order=3,
gap=0,
reverse=False):
from shogun.Kernel import CommUlongStringKernel
from shogun.Features import StringUlongFeatures, StringCharFeatures, DNA
from shogun.PreProc import SortUlongString
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_train_dna)
feats_train = StringUlongFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
preproc = SortUlongString()
preproc.init(feats_train)
feats_train.add_preproc(preproc)
feats_train.apply_preproc()
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_test_dna)
feats_test = StringUlongFeatures(charfeat.get_alphabet())
feats_test.obtain_from_char(charfeat, order - 1, order, gap, reverse)
feats_test.add_preproc(preproc)
feats_test.apply_preproc()
use_sign = False
kernel = CommUlongStringKernel(feats_train, feats_train, use_sign)
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 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 get_weighted_spectrum_kernel(subfeats_list, options):
"""build weighted spectrum kernel with non-redundant k-mer list (removing reverse complement)
Arguments:
subfeats_list -- list of sub-feature objects
options -- object containing option data
Return:
CombinedFeatures of StringWord(Ulong)Features, CombinedKernel of CommWord(Ulong)StringKernel
"""
kmerlen = options.kmerlen
kmerlen2 = options.kmerlen2
subkernels = 0
kernel = CombinedKernel()
feats = CombinedFeatures()
weights = []
i = 0
for subfeats in subfeats_list:
feats.append_feature_obj(subfeats)
combine_kcount = Counter()
for i in xrange(subfeats.get_num_vectors()):
fv = list(subfeats.get_feature_vector(i))
combine_kcount += Counter(fv)
number = len(combine_kcount)
klen = kmerlen + i
for k in xrange(kmerlen, kmerlen2 + 1):
if k <= 8:
subkernel = CommWordStringKernel(10, False)
else:
subkernel = CommUlongStringKernel(10, False)
kernel.append_kernel(subkernel)
subkernels += 1
kernel.init(feats, feats)
# here the weight for each k-mer is uniform
'''
subkernels = 8
numpy.array([1 / float(subkernels)] * subkernels, numpy.dtype('float64'))
array([ 0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125])
'''
kernel.set_subkernel_weights(
numpy.array([1 / float(subkernels)] * subkernels,
numpy.dtype('float64')))
return kernel
def get_spectrum_kernel(feats, options):
"""build spectrum kernel with non-redundant k-mer list (removing reverse complement)
Arguments:
feats -- feature object
options -- object containing option data
Return:
StringWord(Ulong)Features, CommWord(Ulong)StringKernel
"""
if options.kmerlen <= 8:
return CommWordStringKernel(feats, feats)
else:
return CommUlongStringKernel(feats, feats)
def get_weighted_spectrum_kernel(subfeats_list, options):
"""build weighted spectrum kernel with non-redundant k-mer list (removing reverse complement)
Arguments:
subfeats_list -- list of sub-feature objects
options -- object containing option data
Return:
CombinedFeatures of StringWord(Ulong)Features, CombinedKernel of CommWord(Ulong)StringKernel
"""
kmerlen = options.kmerlen
kmerlen2 = options.kmerlen2
subkernels = 0
kernel = CombinedKernel()
feats = CombinedFeatures()
for subfeats in subfeats_list:
feats.append_feature_obj(subfeats)
for k in xrange(kmerlen, kmerlen2 + 1):
if k <= 8:
subkernel = CommWordStringKernel(10, False)
else:
subkernel = CommUlongStringKernel(10, False)
kernel.append_kernel(subkernel)
subkernels += 1
kernel.init(feats, feats)
kernel.set_subkernel_weights(
numpy.array([1 / float(subkernels)] * subkernels,
numpy.dtype('float64')))
return kernel