# This is an example for the initialization of the CommWordString-kernel (aka
# Spectrum or n-gram kernel; its name is derived from the unix command comm). This kernel
# sums over k-mere matches (k='order'). For efficient computing a preprocessor is used
# that extracts and sorts all k-mers. If 'use_sign' is set to one each k-mere is counted
# only once.
from tools.load import LoadMatrix
from sg import sg
lm=LoadMatrix()
traindna=lm.load_dna('../data/fm_train_dna.dat')
testdna=lm.load_dna('../data/fm_test_dna.dat')
parameter_list=[[traindna,testdna,10,3,0,'n',False,'FULL'],
[traindna,testdna,11,4,0,'n',False,'FULL']]
def kernel_commwordstring (fm_train_dna=traindna,fm_test_dna=testdna,
size_cache=10,
order=3,gap=0,reverse='n',
use_sign=False,normalization='FULL'):
sg('add_preproc', 'SORTWORDSTRING')
sg('set_features', 'TRAIN', fm_train_dna, 'DNA')
sg('convert', 'TRAIN', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse)
sg('attach_preproc', 'TRAIN')
sg('set_features', 'TEST', fm_test_dna, 'DNA')
sg('convert', 'TEST', 'STRING', 'CHAR', 'STRING', 'WORD', order, order-1, gap, reverse)
sg('attach_preproc', 'TEST')
sg('set_kernel', 'COMMSTRING', 'WORD', size_cache, use_sign, normalization)
km=sg('get_kernel_matrix', 'TRAIN')
from tools.load import LoadMatrix
lm = LoadMatrix()
traindat = lm.load_dna('../data/fm_train_dna.dat')
testdat = lm.load_dna('../data/fm_test_dna.dat')
parameter_list = [[traindat, testdat, 5, 5], [traindat, testdat, 6, 6]]
def kernel_distantsegments_modular(fm_train_dna=traindat,
fm_test_dna=testdat,
delta=5,
theta=5):
from shogun.Features import StringCharFeatures, DNA
from shogun.Kernel import DistantSegmentsKernel
feats_train = StringCharFeatures(fm_train_dna, DNA)
feats_test = StringCharFeatures(fm_test_dna, DNA)
kernel = DistantSegmentsKernel(feats_train, feats_train, 10, delta, theta)
km_train = kernel.get_kernel_matrix()
kernel.init(feats_train, feats_test)
km_test = kernel.get_kernel_matrix()
return km_train, km_test, kernel
if __name__ == '__main__':
print('DistantSegments')
kernel_distantsegments_modular(*parameter_list[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()
###########################################################################
# call functions
###########################################################################
if __name__=='__main__':
from tools.load import LoadMatrix
lm=LoadMatrix()
fm_dna=lm.load_dna('../data/fm_train_dna.dat')
histogram()
from tools.load import LoadMatrix
lm=LoadMatrix()
traindna = lm.load_dna('../data/fm_train_dna.dat')
parameter_list = [[traindna,3,0,False],[traindna,4,0,False]]
def distribution_histogram_modular (fm_dna=traindna,order=3,gap=0,reverse=False):
from shogun.Features import StringWordFeatures, StringCharFeatures, DNA
from shogun.Distribution import Histogram
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)
out_likelihood = histo.get_log_likelihood()
out_sample = histo.get_log_likelihood_sample()
return histo,out_sample,out_likelihood
###########################################################################
#!/usr/bin/env python
from tools.load import LoadMatrix
lm = LoadMatrix()
train_dna = lm.load_dna("../data/fm_train_dna.dat")
test_dna = lm.load_dna("../data/fm_test_dna.dat")
label = lm.load_labels("../data/label_train_dna.dat")
parameter_list = [[train_dna, test_dna, label, 20, 0.9, 1e-3, 1], [train_dna, test_dna, label, 20, 2.3, 1e-5, 4]]
def classifier_svmlight_batch_linadd_modular(
fm_train_dna, fm_test_dna, label_train_dna, degree, C, epsilon, num_threads
):
from modshogun import StringCharFeatures, BinaryLabels, DNA
from modshogun import WeightedDegreeStringKernel, MSG_DEBUG
try:
from modshogun import SVMLight
except ImportError:
print("No support for SVMLight available.")
return
feats_train = StringCharFeatures(DNA)
# feats_train.io.set_loglevel(MSG_DEBUG)
feats_train.set_features(fm_train_dna)
feats_test = StringCharFeatures(DNA)
feats_test.set_features(fm_test_dna)
degree = 20
