def distance_hammingword_modular (fm_train_dna=traindna,fm_test_dna=testdna, fm_test_real=testdat,order=3,gap=0,reverse=False,use_sign=False): from shogun.Features import StringCharFeatures, StringWordFeatures, DNA from shogun.Preprocessor import SortWordString from shogun.Distance import HammingWordDistance charfeat=StringCharFeatures(DNA) charfeat.set_features(fm_train_dna) feats_train=StringWordFeatures(charfeat.get_alphabet()) feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse) preproc=SortWordString() preproc.init(feats_train) feats_train.add_preprocessor(preproc) feats_train.apply_preprocessor() charfeat=StringCharFeatures(DNA) charfeat.set_features(fm_test_dna) feats_test=StringWordFeatures(charfeat.get_alphabet()) feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse) feats_test.add_preprocessor(preproc) feats_test.apply_preprocessor() distance=HammingWordDistance(feats_train, feats_train, use_sign) dm_train=distance.get_distance_matrix() distance.init(feats_train, feats_test) dm_test=distance.get_distance_matrix() return distance,dm_train,dm_test
def kernel_comm_word_string_modular(fm_train_dna=traindat,
fm_test_dna=testdat,
order=3,
gap=0,
reverse=False,
use_sign=False):
from shogun.Kernel import CommWordStringKernel
from shogun.Features import StringWordFeatures, StringCharFeatures, DNA
from shogun.Preprocessor import SortWordString
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_train_dna)
feats_train = StringWordFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
preproc = SortWordString()
preproc.init(feats_train)
feats_train.add_preproc(preproc)
feats_train.apply_preproc()
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_test_dna)
feats_test = StringWordFeatures(charfeat.get_alphabet())
feats_test.obtain_from_char(charfeat, order - 1, order, gap, reverse)
feats_test.add_preproc(preproc)
feats_test.apply_preproc()
kernel = CommWordStringKernel(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 init_sensor(self, kernel, svs):
f = StringCharFeatures(svs, DNA)
kname = kernel['name']
if kname == 'spectrum':
wf = StringWordFeatures(f.get_alphabet())
wf.obtain_from_char(f, kernel['order'] - 1, kernel['order'], 0, False)
pre = SortWordString()
pre.init(wf)
wf.add_preprocessor(pre)
wf.apply_preprocessor()
f = wf
k = CommWordStringKernel(0, False)
k.set_use_dict_diagonal_optimization(kernel['order'] < 8)
self.preproc = pre
elif kname == 'wdshift':
k = WeightedDegreePositionStringKernel(0, kernel['order'])
k.set_normalizer(IdentityKernelNormalizer())
k.set_shifts(kernel['shift'] *
numpy.ones(f.get_max_vector_length(), dtype=numpy.int32))
k.set_position_weights(1.0 / f.get_max_vector_length() *
numpy.ones(f.get_max_vector_length(), dtype=numpy.float64))
else:
raise "Currently, only wdshift and spectrum kernels supported"
self.kernel = k
self.train_features = f
return (self.kernel, self.train_features)
def distance_hammingword_modular(fm_train_dna=traindna,
fm_test_dna=testdna,
fm_test_real=testdat,
order=3,
gap=0,
reverse=False,
use_sign=False):
from shogun.Features import StringCharFeatures, StringWordFeatures, DNA
from shogun.Preprocessor import SortWordString
from shogun.Distance import HammingWordDistance
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_train_dna)
feats_train = StringWordFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
preproc = SortWordString()
preproc.init(feats_train)
feats_train.add_preprocessor(preproc)
feats_train.apply_preprocessor()
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_test_dna)
feats_test = StringWordFeatures(charfeat.get_alphabet())
feats_test.obtain_from_char(charfeat, order - 1, order, gap, reverse)
feats_test.add_preprocessor(preproc)
feats_test.apply_preprocessor()
distance = HammingWordDistance(feats_train, feats_train, use_sign)
dm_train = distance.get_distance_matrix()
distance.init(feats_train, feats_test)
dm_test = distance.get_distance_matrix()
return distance, dm_train, dm_test
def kernel_weighted_comm_word_string_modular (fm_train_dna=traindat,fm_test_dna=testdat,order=3,gap=0,reverse=True ): from shogun.Kernel import WeightedCommWordStringKernel from shogun.Features import StringWordFeatures, StringCharFeatures, DNA from shogun.Preprocessor import SortWordString charfeat=StringCharFeatures(fm_train_dna, DNA) feats_train=StringWordFeatures(charfeat.get_alphabet()) feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse) preproc=SortWordString() preproc.init(feats_train) feats_train.add_preprocessor(preproc) feats_train.apply_preprocessor() charfeat=StringCharFeatures(fm_test_dna, DNA) feats_test=StringWordFeatures(charfeat.get_alphabet()) feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse) feats_test.add_preprocessor(preproc) feats_test.apply_preprocessor() use_sign=False kernel=WeightedCommWordStringKernel(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 init_sensor(self, kernel, svs):
f = StringCharFeatures(svs, DNA)
kname = kernel['name']
if kname == 'spectrum':
wf = StringWordFeatures(f.get_alphabet())
wf.obtain_from_char(f, kernel['order'] - 1, kernel['order'], 0,
False)
pre = SortWordString()
pre.init(wf)
wf.add_preprocessor(pre)
wf.apply_preprocessor()
f = wf
k = CommWordStringKernel(0, False)
k.set_use_dict_diagonal_optimization(kernel['order'] < 8)
self.preproc = pre
elif kname == 'wdshift':
k = WeightedDegreePositionStringKernel(0, kernel['order'])
k.set_normalizer(IdentityKernelNormalizer())
k.set_shifts(
kernel['shift'] *
numpy.ones(f.get_max_vector_length(), dtype=numpy.int32))
k.set_position_weights(
1.0 / f.get_max_vector_length() *
numpy.ones(f.get_max_vector_length(), dtype=numpy.float64))
else:
raise "Currently, only wdshift and spectrum kernels supported"
self.kernel = k
self.train_features = f
return (self.kernel, self.train_features)
def tests_check_commwordkernel_memleak_modular(num, order, gap, reverse): import gc from shogun.Features import Alphabet,StringCharFeatures,StringWordFeatures,DNA from shogun.Preprocessor import SortWordString, MSG_DEBUG from shogun.Kernel import CommWordStringKernel, IdentityKernelNormalizer from numpy import mat POS=[num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT'] NEG=[num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT'] for i in xrange(10): alpha=Alphabet(DNA) traindat=StringCharFeatures(alpha) traindat.set_features(POS+NEG) trainudat=StringWordFeatures(traindat.get_alphabet()); trainudat.obtain_from_char(traindat, order-1, order, gap, reverse) #trainudat.io.set_loglevel(MSG_DEBUG) pre = SortWordString() #pre.io.set_loglevel(MSG_DEBUG) pre.init(trainudat) trainudat.add_preproc(pre) trainudat.apply_preproc() spec = CommWordStringKernel(10, False) spec.set_normalizer(IdentityKernelNormalizer()) spec.init(trainudat, trainudat) K=spec.get_kernel_matrix() del POS del NEG del order del gap del reverse return K
def tests_check_commwordkernel_memleak_modular (num, order, gap, reverse): import gc from shogun.Features import Alphabet,StringCharFeatures,StringWordFeatures,DNA from shogun.Preprocessor import SortWordString, MSG_DEBUG from shogun.Kernel import CommWordStringKernel, IdentityKernelNormalizer from numpy import mat POS=[num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT'] NEG=[num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'TTGT', num*'TTGT', num*'TTGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT',num*'ACGT', num*'ACGT', num*'ACGT'] for i in range(10): alpha=Alphabet(DNA) traindat=StringCharFeatures(alpha) traindat.set_features(POS+NEG) trainudat=StringWordFeatures(traindat.get_alphabet()); trainudat.obtain_from_char(traindat, order-1, order, gap, reverse) #trainudat.io.set_loglevel(MSG_DEBUG) pre = SortWordString() #pre.io.set_loglevel(MSG_DEBUG) pre.init(trainudat) trainudat.add_preprocessor(pre) trainudat.apply_preprocessor() spec = CommWordStringKernel(10, False) spec.set_normalizer(IdentityKernelNormalizer()) spec.init(trainudat, trainudat) K=spec.get_kernel_matrix() del POS del NEG del order del gap del reverse return K
def create_features(kname, examples, kparam, train_mode, preproc, seq_source, nuc_con):
"""Converts numpy arrays or sequences into shogun features"""
if kname == 'gauss' or kname == 'linear' or kname == 'poly':
examples = numpy.array(examples)
feats = RealFeatures(examples)
elif kname == 'wd' or kname == 'localalign' or kname == 'localimprove':
if seq_source == 'dna':
examples = non_atcg_convert(examples, nuc_con)
feats = StringCharFeatures(examples, DNA)
elif seq_source == 'protein':
examples = non_aminoacid_converter(examples, nuc_con)
feats = StringCharFeatures(examples, PROTEIN)
else:
sys.stderr.write("Sequence source -"+seq_source+"- is invalid. select [dna|protein]\n")
sys.exit(-1)
elif kname == 'spec' or kname == 'cumspec':
if seq_source == 'dna':
examples = non_atcg_convert(examples, nuc_con)
feats = StringCharFeatures(examples, DNA)
elif seq_source == 'protein':
examples = non_aminoacid_converter(examples, nuc_con)
feats = StringCharFeatures(examples, PROTEIN)
else:
sys.stderr.write("Sequence source -"+seq_source+"- is invalid. select [dna|protein]\n")
sys.exit(-1)
wf = StringUlongFeatures( feats.get_alphabet() )
wf.obtain_from_char(feats, kparam['degree']-1, kparam['degree'], 0, kname=='cumspec')
del feats
if train_mode:
preproc = SortUlongString()
preproc.init(wf)
wf.add_preprocessor(preproc)
ret = wf.apply_preprocessor()
#assert(ret)
feats = wf
elif kname == 'spec2' or kname == 'cumspec2':
# spectrum kernel on two sequences
feats = {}
feats['combined'] = CombinedFeatures()
reversed = kname=='cumspec2'
(ex0,ex1) = zip(*examples)
f0 = StringCharFeatures(list(ex0), DNA)
wf = StringWordFeatures(f0.get_alphabet())
wf.obtain_from_char(f0, kparam['degree']-1, kparam['degree'], 0, reversed)
del f0
if train_mode:
preproc = SortWordString()
preproc.init(wf)
wf.add_preprocessor(preproc)
ret = wf.apply_preprocessor()
assert(ret)
feats['combined'].append_feature_obj(wf)
feats['f0'] = wf
f1 = StringCharFeatures(list(ex1), DNA)
wf = StringWordFeatures( f1.get_alphabet() )
wf.obtain_from_char(f1, kparam['degree']-1, kparam['degree'], 0, reversed)
del f1
if train_mode:
preproc = SortWordString()
preproc.init(wf)
wf.add_preprocessor(preproc)
ret = wf.apply_preprocessor()
assert(ret)
feats['combined'].append_feature_obj(wf)
feats['f1'] = wf
else:
print 'Unknown kernel %s' % kname
return (feats,preproc)