def kernel_comm_ulong_string_modular(fm_train_dna=traindat,
fm_test_dna=testdat,
order=3,
gap=0,
reverse=False):
from modshogun import CommUlongStringKernel
from modshogun import StringUlongFeatures, StringCharFeatures, DNA
from modshogun 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)
preproc = SortUlongString()
preproc.init(feats_train)
feats_train.add_preprocessor(preproc)
feats_train.apply_preprocessor()
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_preprocessor(preproc)
feats_test.apply_preprocessor()
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()
return km_train, km_test, kernel
def runShogunSVMDNAUlongSpectrumKernel(train_xt, train_lt, test_xt):
"""
run svm with ulong spectrum kernel
"""
##################################################
# set up svr
charfeat_train = StringCharFeatures(train_xt, DNA)
feats_train = StringUlongFeatures(DNA)
feats_train.obtain_from_char(charfeat_train, K - 1, K, GAP, False)
preproc = SortUlongString()
preproc.init(feats_train)
feats_train.add_preprocessor(preproc)
feats_train.apply_preprocessor()
charfeat_test = StringCharFeatures(test_xt, DNA)
feats_test = StringUlongFeatures(DNA)
feats_test.obtain_from_char(charfeat_test, K - 1, K, GAP, False)
feats_test.add_preprocessor(preproc)
feats_test.apply_preprocessor()
kernel = CommUlongStringKernel(feats_train, feats_train, False)
kernel.io.set_loglevel(MSG_DEBUG)
# init kernel
labels = BinaryLabels(train_lt)
# run svm model
print "Ready to train!"
svm = LibSVM(SVMC, kernel, labels)
svm.io.set_loglevel(MSG_DEBUG)
svm.train()
# predictions
print "Making predictions!"
out1DecisionValues = svm.apply(feats_train)
out1 = out1DecisionValues.get_labels()
kernel.init(feats_train, feats_test)
out2DecisionValues = svm.apply(feats_test)
out2 = svm.apply(feats_test).get_labels()
return out1, out2, out1DecisionValues, out2DecisionValues
def features_string_ulong_modular (start=0,order=2,gap=0,rev=False):
from modshogun import StringCharFeatures, StringUlongFeatures, RAWBYTE
from numpy import array, uint64
#create string features
cf=StringCharFeatures(['hey','guys','string'], RAWBYTE)
uf=StringUlongFeatures(RAWBYTE)
uf.obtain_from_char(cf, start,order,gap,rev)
#replace string 0
uf.set_feature_vector(array([1,2,3,4,5], dtype=uint64), 0)
return uf.get_features(),uf.get_feature_vector(2), uf.get_num_vectors()
