Python StringCharFeatures.set_features方法代码示例

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def svm_light ():
	print 'SVMLight'

	from shogun.Features import StringCharFeatures, Labels, DNA
	from shogun.Kernel import WeightedDegreeStringKernel
	try:
		from shogun.Classifier import SVMLight
	except ImportError:
		print 'No support for SVMLight available.'
		return

	feats_train=StringCharFeatures(DNA)
	feats_train.set_features(fm_train_dna)
	feats_test=StringCharFeatures(DNA)
	feats_test.set_features(fm_test_dna)
	degree=20

	kernel=WeightedDegreeStringKernel(feats_train, feats_train, degree)

	C=1.2
	epsilon=1e-5
	num_threads=1
	labels=Labels(label_train_dna)

	svm=SVMLight(C, kernel, labels)
	svm.set_epsilon(epsilon)
	svm.parallel.set_num_threads(num_threads)
	svm.train()

	kernel.init(feats_train, feats_test)
	svm.classify().get_labels()

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def classifier_svmlight_modular (fm_train_dna=traindat,fm_test_dna=testdat,label_train_dna=label_traindat,C=1.2,epsilon=1e-5,num_threads=1):
	from shogun.Features import StringCharFeatures, Labels, DNA
	from shogun.Kernel import WeightedDegreeStringKernel
	try:
		from shogun.Classifier import SVMLight
	except ImportError:
		print 'No support for SVMLight available.'
		return

	feats_train=StringCharFeatures(DNA)
	feats_train.set_features(fm_train_dna)
	feats_test=StringCharFeatures(DNA)
	feats_test.set_features(fm_test_dna)
	degree=20

	kernel=WeightedDegreeStringKernel(feats_train, feats_train, degree)

	labels=Labels(label_train_dna)

	svm=SVMLight(C, kernel, labels)
	svm.set_epsilon(epsilon)
	svm.parallel.set_num_threads(num_threads)
	svm.train()

	kernel.init(feats_train, feats_test)
	svm.apply().get_labels()
	return kernel

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def linear_hmm ():
	print 'LinearHMM'

	from shogun.Features import StringWordFeatures, StringCharFeatures, DNA
	from shogun.Distribution import LinearHMM

	order=3
	gap=0
	reverse=False

	charfeat=StringCharFeatures(DNA)
	charfeat.set_features(fm_dna)
	feats=StringWordFeatures(charfeat.get_alphabet())
	feats.obtain_from_char(charfeat, order-1, order, gap, reverse)

	hmm=LinearHMM(feats)
	hmm.train()

	hmm.get_transition_probs()

	num_examples=feats.get_num_vectors()
	num_param=hmm.get_num_model_parameters()
	for i in xrange(num_examples):
		for j in xrange(num_param):
			hmm.get_log_derivative(j, i)

	hmm.get_log_likelihood()
	hmm.get_log_likelihood_sample()

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
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()

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def kernel_histogram_word_string_modular(
    fm_train_dna=traindat, fm_test_dna=testdat, label_train_dna=label_traindat, order=3, gap=0, reverse=False
):

    from shogun.Features import StringCharFeatures, StringWordFeatures, DNA, Labels
    from shogun.Kernel import HistogramWordStringKernel
    from shogun.Classifier import PluginEstimate  # , MSG_DEBUG

    reverse = reverse
    charfeat = StringCharFeatures(DNA)
    # charfeat.io.set_loglevel(MSG_DEBUG)
    charfeat.set_features(fm_train_dna)
    feats_train = StringWordFeatures(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 = StringWordFeatures(charfeat.get_alphabet())
    feats_test.obtain_from_char(charfeat, order - 1, order, gap, reverse)

    pie = PluginEstimate()
    labels = Labels(label_train_dna)
    pie.set_labels(labels)
    pie.set_features(feats_train)
    pie.train()

    kernel = HistogramWordStringKernel(feats_train, feats_train, pie)
    km_train = kernel.get_kernel_matrix()
    kernel.init(feats_train, feats_test)
    pie.set_features(feats_test)
    pie.classify().get_labels()
    km_test = kernel.get_kernel_matrix()
    return km_train, km_test, kernel

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
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

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
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

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def manhattan_word_distance ():
	print 'ManhattanWordDistance'

	from shogun.Features import StringCharFeatures, StringWordFeatures, DNA
	from shogun.PreProc import SortWordString
	from shogun.Distance import ManhattanWordDistance

	order=3
	gap=0
	reverse=False

	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()

	distance=ManhattanWordDistance(feats_train, feats_train)

	dm_train=distance.get_distance_matrix()
	distance.init(feats_train, feats_test)
	dm_test=distance.get_distance_matrix()

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def distribution_linearhmm_modular (fm_dna=traindna,order=3,gap=0,reverse=False):

	from shogun.Features import StringWordFeatures, StringCharFeatures, DNA
	from shogun.Distribution import LinearHMM

	charfeat=StringCharFeatures(DNA)
	charfeat.set_features(fm_dna)
	feats=StringWordFeatures(charfeat.get_alphabet())
	feats.obtain_from_char(charfeat, order-1, order, gap, reverse)

	hmm=LinearHMM(feats)
	hmm.train()

	hmm.get_transition_probs()

	num_examples=feats.get_num_vectors()
	num_param=hmm.get_num_model_parameters()
	for i in range(num_examples):
		for j in range(num_param):
			hmm.get_log_derivative(j, i)

	out_likelihood = hmm.get_log_likelihood()
	out_sample = hmm.get_log_likelihood_sample()

	return hmm,out_likelihood ,out_sample

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def distribution_hmm_modular(fm_cube, N, M, pseudo, order, gap, reverse, num_examples):
	from shogun.Features import StringWordFeatures, StringCharFeatures, CUBE
	from shogun.Distribution import HMM, BW_NORMAL

	charfeat=StringCharFeatures(CUBE)
	charfeat.set_features(fm_cube)
	feats=StringWordFeatures(charfeat.get_alphabet())
	feats.obtain_from_char(charfeat, order-1, order, gap, reverse)

	hmm=HMM(feats, N, M, pseudo)
	hmm.train()
	hmm.baum_welch_viterbi_train(BW_NORMAL)

	num_examples=feats.get_num_vectors()
	num_param=hmm.get_num_model_parameters()
	for i in xrange(num_examples):
		for j in xrange(num_param):
			hmm.get_log_derivative(j, i)

	best_path=0
	best_path_state=0
	for i in xrange(num_examples):
		best_path+=hmm.best_path(i)
		for j in xrange(N):
			best_path_state+=hmm.get_best_path_state(i, j)

	lik_example = hmm.get_log_likelihood()
	lik_sample = hmm.get_log_likelihood_sample()

	return lik_example, lik_sample, hmm

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def histogram ():
	print 'Histogram'

	from shogun.Features import StringWordFeatures, StringCharFeatures, DNA
	from shogun.Distribution import Histogram

	order=3
	gap=0
	reverse=False

	charfeat=StringCharFeatures(DNA)
	charfeat.set_features(fm_dna)
	feats=StringWordFeatures(charfeat.get_alphabet())
	feats.obtain_from_char(charfeat, order-1, order, gap, reverse)

	histo=Histogram(feats)
	histo.train()

	histo.get_histogram()

	num_examples=feats.get_num_vectors()
	num_param=histo.get_num_model_parameters()
	#for i in xrange(num_examples):
	#	for j in xrange(num_param):
	#		histo.get_log_derivative(j, i)

	histo.get_log_likelihood()
	histo.get_log_likelihood_sample()

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def classifier_svmlight_linear_term_modular(fm_train_dna=traindna,fm_test_dna=testdna, \
                                                label_train_dna=label_traindna,degree=3, \
                                                C=10,epsilon=1e-5,num_threads=1):
    
    from shogun.Features import StringCharFeatures, BinaryLabels, DNA
    from shogun.Kernel import WeightedDegreeStringKernel
    from shogun.Classifier import SVMLight
    
    feats_train=StringCharFeatures(DNA)
    feats_train.set_features(fm_train_dna)
    feats_test=StringCharFeatures(DNA)
    feats_test.set_features(fm_test_dna)
    
    kernel=WeightedDegreeStringKernel(feats_train, feats_train, degree)
    
    labels=BinaryLabels(label_train_dna)
    
    svm=SVMLight(C, kernel, labels)
    svm.set_qpsize(3)
    svm.set_linear_term(-numpy.array([1,2,3,4,5,6,7,8,7,6], dtype=numpy.double));
    svm.set_epsilon(epsilon)
    svm.parallel.set_num_threads(num_threads)
    svm.train()
    
    kernel.init(feats_train, feats_test)
    out = svm.apply().get_labels()
    return out,kernel

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
def plugin_estimate_histogram ():
	print 'PluginEstimate w/ HistogramWord'
	from shogun.Features import StringCharFeatures, StringWordFeatures, DNA, Labels
	from shogun.Kernel import HistogramWordStringKernel
	from shogun.Classifier import PluginEstimate

	order=3
	gap=0
	reverse=False

	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)

	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)

	pie=PluginEstimate()
	labels=Labels(label_train_dna)
	pie.set_labels(labels)
	pie.set_features(feats_train)
	pie.train()

	kernel=HistogramWordStringKernel(feats_train, feats_train, pie)
	km_train=kernel.get_kernel_matrix()

	kernel.init(feats_train, feats_test)
	pie.set_features(feats_test)
	pie.classify().get_labels()
	km_test=kernel.get_kernel_matrix()

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
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

# 需要导入模块: from shogun.Features import StringCharFeatures [as 别名]
# 或者: from shogun.Features.StringCharFeatures import set_features [as 别名]
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.PreProc 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