Python Features.StringCharFeatures类代码示例

def plugin_estimate_salzberg ():
	print 'PluginEstimate w/ SalzbergWord'

	from shogun.Features import StringCharFeatures, StringWordFeatures, DNA, Labels
	from shogun.Kernel import SalzbergWordStringKernel
	from shogun.Classifier import PluginEstimate

	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)

	charfeat=StringCharFeatures(fm_test_dna, 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=SalzbergWordStringKernel(feats_train, feats_test, pie, labels)
	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()

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

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

def create_hashed_features_spectrum(param, data):
    """
    creates hashed dot features for the spectrum kernel
    """

    # extract parameters
    order = param["degree_spectrum"]

    # fixed parameters
    gap = 0
    reverse = True 
    normalize = True

    # create features
    feats_char = StringCharFeatures(data, DNA)
    feats_word = StringWordFeatures(feats_char.get_alphabet())
    feats_word.obtain_from_char(feats_char, order-1, order, gap, reverse)

    # create preproc
    preproc = SortWordString()
    preproc.init(feats_word)
    feats_word.add_preproc(preproc)
    feats_word.apply_preproc()

    # finish 
    feats = ImplicitWeightedSpecFeatures(feats_word, normalize)

    return feats

def create_promoter_features(data, param):
    """
    creates promoter combined features
    
    @param examples:
    @param param:
    """

    print "creating promoter features"

    (center, left, right) = split_data_promoter(data, param["center_offset"], param["center_pos"])

    # set up base features
    feat_center = StringCharFeatures(DNA)
    feat_center.set_features(center)
    feat_left = get_spectrum_features(left)
    feat_right = get_spectrum_features(right)

    # construct combined features
    feat = CombinedFeatures()
    feat.append_feature_obj(feat_center)
    feat.append_feature_obj(feat_left)
    feat.append_feature_obj(feat_right)

    return feat

    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 get_predictions_from_seqdict(self, seqdic, site):
		""" we need to generate a huge test features object
			containing all locations found in each seqdict-sequence
			and each location (this is necessary to efficiently
			(==fast,low memory) compute the splice outputs
		"""

		seqlen=self.window_right+self.window_left+2

		for s in seqdic:
			position_list=DynamicIntArray()

			sequence=s.seq
			positions=s.preds[site].positions
			for j in xrange(len(positions)):
				i=positions[j] - self.offset -self.window_left
				position_list.append_element(i)

			t=StringCharFeatures([sequence], DNA)
			t.obtain_by_position_list(seqlen, position_list)
			self.wd_kernel.init(self.traindat, t)

			self.wd_kernel.io.enable_progress()
			l=self.svm.apply().get_values()
			self.wd_kernel.cleanup()
			sys.stdout.write("\n...done...\n")

			num=len(s.preds[site].positions)
			scores= num * [0]
			for j in xrange(num):
				scores[j]=l[j]
			s.preds[site].set_scores(scores)

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 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()

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_salzberg_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 SalzbergWordStringKernel
	from shogun.Classifier import PluginEstimate

	charfeat=StringCharFeatures(fm_train_dna, DNA)
	feats_train=StringWordFeatures(charfeat.get_alphabet())
	feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)

	charfeat=StringCharFeatures(fm_test_dna, 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=SalzbergWordStringKernel(feats_train, feats_train, pie, labels)
	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

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.PreProc 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 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 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()

def get_wd_features(data, feat_type="dna"):
    """
    create feature object for wdk
    """
    if feat_type == "dna":
        feat = StringCharFeatures(DNA)
    elif feat_type == "protein":
        feat = StringCharFeatures(PROTEIN)
    else:
        raise Exception("unknown feature type")
    feat.set_features(data)

    return feat