Python StringWordFeatures.add_preprocessor Exemples

Exemple #1

Fichier : signal_sensor.py Projet : Anshul-Bansal/gsoc

    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)

Exemple #2

Fichier : distance_hammingword_modular.py Projet : behollis/muViewBranch

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

Exemple #3

Fichier : kernel_comm_word_string_modular.py Projet : theoryno3/shogun

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_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()

	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

Exemple #4

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

Exemple #5

Fichier : kernel_weighted_comm_word_string_modular.py Projet : Anshul-Bansal/gsoc

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

Exemple #6

Fichier : signal_sensor.py Projet : nuoanunu/shogun-olaf

    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)

Exemple #7

def get_spectrum_features(data, order=3, gap=0, reverse=True):
    """
    create feature object used by spectrum kernel
    """

    charfeat = StringCharFeatures(data, DNA)
    feat = StringWordFeatures(charfeat.get_alphabet())
    feat.obtain_from_char(charfeat, order - 1, order, gap, reverse)
    preproc = SortWordString()
    preproc.init(feat)
    feat.add_preprocessor(preproc)
    feat.apply_preprocessor()

    return feat

Exemple #8

Fichier : serialization_string_kernels_modular.py Projet : monalisag/shogun

def get_spectrum_features(data, order=3, gap=0, reverse=True):
    """
    create feature object used by spectrum kernel
    """

    charfeat = StringCharFeatures(data, DNA)
    feat = StringWordFeatures(charfeat.get_alphabet())
    feat.obtain_from_char(charfeat, order-1, order, gap, reverse)
    preproc = SortWordString()
    preproc.init(feat)
    feat.add_preprocessor(preproc)
    feat.apply_preprocessor()

    return feat

Exemple #9

Fichier : tests_check_commwordkernel_memleak_modular.py Projet : theoryno3/shogun

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