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 modshogun import StringCharFeatures, StringWordFeatures, DNA, BinaryLabels
from modshogun import SalzbergWordStringKernel
from modshogun 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 = BinaryLabels(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.apply().get_labels()
km_test = kernel.get_kernel_matrix()
return km_train, km_test, kernel
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 modshogun import StringCharFeatures, StringWordFeatures, DNA, BinaryLabels from modshogun import HistogramWordStringKernel from modshogun 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=BinaryLabels(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.apply().get_labels() km_test=kernel.get_kernel_matrix() return km_train,km_test,kernel
def kernel_histogram_word_string_modular (fm_train_dna=traindat,fm_test_dna=testdat,label_train_dna=label_traindat,order=3,ppseudo_count=1,npseudo_count=1): from modshogun import StringCharFeatures, StringWordFeatures, DNA, BinaryLabels from modshogun import HistogramWordStringKernel, AvgDiagKernelNormalizer from modshogun import PluginEstimate#, MSG_DEBUG 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, 0, False) charfeat=StringCharFeatures(DNA) charfeat.set_features(fm_test_dna) feats_test=StringWordFeatures(charfeat.get_alphabet()) feats_test.obtain_from_char(charfeat, order-1, order, 0, False) pie=PluginEstimate(ppseudo_count,npseudo_count) labels=BinaryLabels(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.apply().get_labels() km_test=kernel.get_kernel_matrix() return km_train,km_test,kernel
def _evaluate_pie (indata, prefix): pie=PluginEstimate() feats=util.get_features(indata, prefix) labels=BinaryLabels(double(indata['classifier_labels'])) pie.set_labels(labels) pie.set_features(feats['train']) pie.train() fun=eval(indata[prefix+'name']+'Kernel') kernel=fun(feats['train'], feats['train'], pie) km_train=max(abs( indata[prefix+'matrix_train']-kernel.get_kernel_matrix()).flat) kernel.init(feats['train'], feats['test']) pie.set_features(feats['test']) km_test=max(abs( indata[prefix+'matrix_test']-kernel.get_kernel_matrix()).flat) classified=max(abs( pie.apply().get_values()-indata['classifier_classified'])) return util.check_accuracy(indata[prefix+'accuracy'], km_train=km_train, km_test=km_test, classified=classified)
def _evaluate_pie(indata, prefix):
pie = PluginEstimate()
feats = util.get_features(indata, prefix)
labels = BinaryLabels(double(indata['classifier_labels']))
pie.set_labels(labels)
pie.set_features(feats['train'])
pie.train()
fun = eval(indata[prefix + 'name'] + 'Kernel')
kernel = fun(feats['train'], feats['train'], pie)
km_train = max(
abs(indata[prefix + 'matrix_train'] - kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
pie.set_features(feats['test'])
km_test = max(
abs(indata[prefix + 'matrix_test'] - kernel.get_kernel_matrix()).flat)
classified = max(
abs(pie.apply().get_values() - indata['classifier_classified']))
return util.check_accuracy(indata[prefix + 'accuracy'],
km_train=km_train,
km_test=km_test,
classified=classified)