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 preproc_sortwordstring_modular (fm_train_dna=traindna,fm_test_dna=testdna,order=3,gap=0,reverse=False,use_sign=False): from shogun.Kernel import CommWordStringKernel from shogun.Features import StringCharFeatures, StringWordFeatures, 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_preproc(preproc) feats_train.apply_preproc() 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_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 sort_word_string (): print 'CommWordString' from shogun.Kernel import CommWordStringKernel from shogun.Features import StringCharFeatures, StringWordFeatures, DNA from shogun.PreProc import SortWordString order=3 gap=0 reverse=False 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_preproc(preproc) feats_train.apply_preproc() 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_preproc(preproc) feats_test.apply_preproc() use_sign=False 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()
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_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 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 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_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
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 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)
100*'ACGT',100*'ACGT', 100*'ACGT', 100*'ACGT',100*'ACGT', 100*'ACGT', 100*'ACGT',100*'ACGT', 100*'ACGT', 100*'ACGT',100*'ACGT', 100*'ACGT', 100*'ACGT',100*'ACGT', 100*'ACGT', 100*'ACGT',100*'ACGT', 100*'ACGT', 100*'ACGT',100*'ACGT', 100*'ACGT', 100*'ACGT'] order=7 gap=0 reverse=False 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=mat(spec.get_kernel_matrix()) del POS del NEG del order del gap del reverse