def classifier_ssk_modular(fm_train_dna=traindat,
fm_test_dna=testdat,
label_train_dna=label_traindat,
C=1,
maxlen=1,
decay=1):
from modshogun import StringCharFeatures, BinaryLabels
from modshogun import LibSVM, StringSubsequenceKernel, DNA
from modshogun import ErrorRateMeasure
feats_train = StringCharFeatures(fm_train_dna, DNA)
feats_test = StringCharFeatures(fm_test_dna, DNA)
labels = BinaryLabels(label_train_dna)
kernel = StringSubsequenceKernel(feats_train, feats_train, maxlen, decay)
svm = LibSVM(C, kernel, labels)
svm.train()
out = svm.apply(feats_train)
evaluator = ErrorRateMeasure()
trainerr = evaluator.evaluate(out, labels)
# print(trainerr)
kernel.init(feats_train, feats_test)
predicted_labels = svm.apply(feats_test).get_labels()
# print predicted_labels
return predicted_labels
def runShogunSVMDNALocalAlignmentKernel(train_xt, train_lt, test_xt):
"""
run svm with spectrum kernel
"""
##################################################
# set up svm
feats_train = StringCharFeatures(train_xt, DNA)
feats_test = StringCharFeatures(test_xt, DNA)
kernel=LocalAlignmentStringKernel(feats_train, feats_train)
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!"
out1=svm.apply(feats_train).get_labels()
kernel.init(feats_train, feats_test)
out2=svm.apply(feats_test).get_labels()
return out1,out2
def runShogunSVMDNALinearStringKernel(train_xt, train_lt, test_xt):
"""
run svm with spectrum kernel
"""
##################################################
# set up svm
feats_train = StringCharFeatures(train_xt, DNA)
feats_test = StringCharFeatures(test_xt, DNA)
kernel = LinearStringKernel(feats_train, feats_train)
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!"
out1 = svm.apply(feats_train).get_labels()
kernel.init(feats_train, feats_test)
out2 = svm.apply(feats_test).get_labels()
return out1, out2
def runShogunSVMDNAWDNoPositionKernel(train_xt, train_lt, test_xt):
"""
run svm with non-position WD kernel
"""
##################################################
# set up svm
feats_train = StringCharFeatures(train_xt, DNA)
feats_test = StringCharFeatures(test_xt, DNA)
kernel = WeightedDegreeStringKernel(feats_train, feats_train, DEGREE)
kernel.io.set_loglevel(MSG_DEBUG)
weights=arange(1,DEGREE+1,dtype=double)[::-1]/ \
sum(arange(1,DEGREE+1,dtype=double))
kernel.set_wd_weights(weights)
# 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!"
out1 = svm.apply(feats_train).get_labels()
kernel.init(feats_train, feats_test)
out2 = svm.apply(feats_test).get_labels()
return out1, out2
def runShogunSVMDNASubsequenceStringKernel(train_xt, train_lt, test_xt):
"""
run svm with spectrum kernel
"""
##################################################
# set up svm
feats_train = StringCharFeatures(train_xt, DNA)
feats_test = StringCharFeatures(test_xt, DNA)
kernel = SubsequenceStringKernel(feats_train, feats_train, MAXLEN, DECAY)
kernel.io.set_loglevel(MSG_DEBUG)
kernel.init(feats_train, feats_train)
# 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 = out2DecisionValues.get_labels()
return out1, out2, out1DecisionValues, out2DecisionValues
def runShogunSVMDNAWDKernel(train_xt, train_lt, test_xt):
"""
run svm with string kernels
"""
##################################################
# set up svm
feats_train = StringCharFeatures(train_xt, DNA)
feats_test = StringCharFeatures(test_xt, DNA)
kernel = WeightedDegreePositionStringKernel(feats_train, feats_train,
DEGREE)
kernel.io.set_loglevel(MSG_DEBUG)
kernel.set_shifts(NUMSHIFTS * ones(len(train_xt[0]), dtype=int32))
kernel.set_position_weights(ones(len(train_xt[0]), dtype=float64))
# 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 = out2DecisionValues.get_labels()
return out1, out2, out1DecisionValues, out2DecisionValues
def runShogunSVMDNAOligoStringKernel(train_xt, train_lt, test_xt):
"""
run svm with spectrum kernel
"""
##################################################
# set up svm
feats_train = StringCharFeatures(train_xt, DNA)
feats_test = StringCharFeatures(test_xt, DNA)
kernel=OligoStringKernel(10, K, WIDTH)
kernel.io.set_loglevel(MSG_DEBUG)
kernel.init(feats_train, feats_train)
# 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=out2DecisionValues.get_labels()
return out1,out2,out1DecisionValues,out2DecisionValues
def runShogunSVMDNACombinedSpectrumKernel(train_xt, train_lt, test_xt):
"""
run svm with combined spectrum kernel
"""
##################################################
# set up svm
kernel=CombinedKernel()
feats_train=CombinedFeatures()
feats_test=CombinedFeatures()
for K in KList:
# Iterate through the K's and make a spectrum kernel for each
charfeat_train = StringCharFeatures(train_xt, DNA)
current_feats_train = StringWordFeatures(DNA)
current_feats_train.obtain_from_char(charfeat_train, K-1, K, GAP, False)
preproc=SortWordString()
preproc.init(current_feats_train)
current_feats_train.add_preprocessor(preproc)
current_feats_train.apply_preprocessor()
feats_train.append_feature_obj(current_feats_train)
charfeat_test = StringCharFeatures(test_xt, DNA)
current_feats_test=StringWordFeatures(DNA)
current_feats_test.obtain_from_char(charfeat_test, K-1, K, GAP, False)
current_feats_test.add_preprocessor(preproc)
current_feats_test.apply_preprocessor()
feats_test.append_feature_obj(current_feats_test)
current_kernel=CommWordStringKernel(10, False)
kernel.append_kernel(current_kernel)
kernel.io.set_loglevel(MSG_DEBUG)
# init kernel
labels = BinaryLabels(train_lt)
# run svm model
print "Ready to train!"
kernel.init(feats_train, feats_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=out2DecisionValues.get_labels()
return out1,out2,out1DecisionValues,out2DecisionValues
def kernel_combined_custom_poly_modular(train_fname=traindat,
test_fname=testdat,
train_label_fname=label_traindat):
from modshogun import CombinedFeatures, RealFeatures, BinaryLabels
from modshogun import CombinedKernel, PolyKernel, CustomKernel
from modshogun import LibSVM, CSVFile
kernel = CombinedKernel()
feats_train = CombinedFeatures()
tfeats = RealFeatures(CSVFile(train_fname))
tkernel = PolyKernel(10, 3)
tkernel.init(tfeats, tfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_train = RealFeatures(CSVFile(train_fname))
feats_train.append_feature_obj(subkfeats_train)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_train)
labels = BinaryLabels(CSVFile(train_label_fname))
svm = LibSVM(1.0, kernel, labels)
svm.train()
kernel = CombinedKernel()
feats_pred = CombinedFeatures()
pfeats = RealFeatures(CSVFile(test_fname))
tkernel = PolyKernel(10, 3)
tkernel.init(tfeats, pfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_test = RealFeatures(CSVFile(test_fname))
feats_pred.append_feature_obj(subkfeats_test)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_pred)
svm.set_kernel(kernel)
svm.apply()
km_train = kernel.get_kernel_matrix()
return km_train, kernel
def kernel_combined_custom_poly_modular (train_fname = traindat,test_fname = testdat,train_label_fname=label_traindat):
from modshogun import CombinedFeatures, RealFeatures, BinaryLabels
from modshogun import CombinedKernel, PolyKernel, CustomKernel
from modshogun import LibSVM, CSVFile
kernel = CombinedKernel()
feats_train = CombinedFeatures()
tfeats = RealFeatures(CSVFile(train_fname))
tkernel = PolyKernel(10,3)
tkernel.init(tfeats, tfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_train = RealFeatures(CSVFile(train_fname))
feats_train.append_feature_obj(subkfeats_train)
subkernel = PolyKernel(10,2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_train)
labels = BinaryLabels(CSVFile(train_label_fname))
svm = LibSVM(1.0, kernel, labels)
svm.train()
kernel = CombinedKernel()
feats_pred = CombinedFeatures()
pfeats = RealFeatures(CSVFile(test_fname))
tkernel = PolyKernel(10,3)
tkernel.init(tfeats, pfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_test = RealFeatures(CSVFile(test_fname))
feats_pred.append_feature_obj(subkfeats_test)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_pred)
svm.set_kernel(kernel)
svm.apply()
km_train=kernel.get_kernel_matrix()
return km_train,kernel
def classifier_custom_kernel_modular(C=1, dim=7):
from modshogun import RealFeatures, BinaryLabels, CustomKernel, LibSVM
from numpy import diag, ones, sign
from numpy.random import rand, seed
seed((C, dim))
lab = sign(2 * rand(dim) - 1)
data = rand(dim, dim)
symdata = data * data.T + diag(ones(dim))
kernel = CustomKernel()
kernel.set_full_kernel_matrix_from_full(data)
labels = BinaryLabels(lab)
svm = LibSVM(C, kernel, labels)
svm.train()
predictions = svm.apply()
out = svm.apply().get_labels()
return svm, out
def classifier_custom_kernel_modular (C=1,dim=7):
from modshogun import RealFeatures, BinaryLabels, CustomKernel, LibSVM
from numpy import diag,ones,sign
from numpy.random import rand,seed
seed((C,dim))
lab=sign(2*rand(dim) - 1)
data=rand(dim, dim)
symdata=data*data.T + diag(ones(dim))
kernel=CustomKernel()
kernel.set_full_kernel_matrix_from_full(data)
labels=BinaryLabels(lab)
svm=LibSVM(C, kernel, labels)
svm.train()
predictions =svm.apply()
out=svm.apply().get_labels()
return svm,out
def runShogunSVMDNASpectrumKernel(train_xt, train_lt, test_xt):
"""
run svm with spectrum kernel
"""
##################################################
# set up svr
charfeat_train = StringCharFeatures(train_xt, DNA)
feats_train = StringWordFeatures(DNA)
feats_train.obtain_from_char(charfeat_train, K - 1, K, GAP, False)
preproc = SortWordString()
preproc.init(feats_train)
feats_train.add_preprocessor(preproc)
feats_train.apply_preprocessor()
charfeat_test = StringCharFeatures(test_xt, DNA)
feats_test = StringWordFeatures(DNA)
feats_test.obtain_from_char(charfeat_test, K - 1, K, GAP, False)
feats_test.add_preprocessor(preproc)
feats_test.apply_preprocessor()
kernel = CommWordStringKernel(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 = out2DecisionValues.get_labels()
return out1, out2, out1DecisionValues, out2DecisionValues
def runShogunSVMProteinPolyMatchSpectrumKernel(train_xt, train_lt, test_xt):
"""
run svm with spectrum kernel
"""
##################################################
# set up svm
charfeat_train = StringCharFeatures(train_xt, DNA)
feats_train = StringWordFeatures(DNA)
feats_train.obtain_from_char(charfeat_train, K-1, K, GAP, False)
preproc=SortWordString()
preproc.init(feats_train)
feats_train.add_preprocessor(preproc)
feats_train.apply_preprocessor()
charfeat_test = StringCharFeatures(test_xt, DNA)
feats_test=StringWordFeatures(DNA)
feats_test.obtain_from_char(charfeat_test, K-1, K, GAP, False)
feats_test.add_preprocessor(preproc)
feats_test.apply_preprocessor()
kernel=PolyMatchWordStringKernel(feats_train, feats_train, DEGREE, True)
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=out2DecisionValues.get_labels()
return out1,out2,out1DecisionValues,out2DecisionValues
def classifier_ssk_modular (fm_train_dna=traindat,fm_test_dna=testdat, label_train_dna=label_traindat,C=1,maxlen=1,decay=1): from modshogun import StringCharFeatures, BinaryLabels from modshogun import LibSVM, StringSubsequenceKernel, DNA from modshogun import ErrorRateMeasure feats_train=StringCharFeatures(fm_train_dna, DNA) feats_test=StringCharFeatures(fm_test_dna, DNA) labels=BinaryLabels(label_train_dna) kernel=StringSubsequenceKernel(feats_train, feats_train, maxlen, decay); svm=LibSVM(C, kernel, labels); svm.train(); out=svm.apply(feats_train); evaluator = ErrorRateMeasure() trainerr = evaluator.evaluate(out,labels) # print(trainerr) kernel.init(feats_train, feats_test) predicted_labels=svm.apply(feats_test).get_labels() # print predicted_labels return predicted_labels
def classifier_libsvm_minimal_modular (train_fname=traindat,test_fname=testdat,label_fname=label_traindat,width=2.1,C=1): from modshogun import RealFeatures, BinaryLabels from modshogun import LibSVM, GaussianKernel, CSVFile from modshogun import ErrorRateMeasure feats_train=RealFeatures(CSVFile(train_fname)) feats_test=RealFeatures(CSVFile(test_fname)) labels=BinaryLabels(CSVFile(label_fname)) kernel=GaussianKernel(feats_train, feats_train, width); svm=LibSVM(C, kernel, labels); svm.train(); out=svm.apply(feats_train); evaluator = ErrorRateMeasure() testerr = evaluator.evaluate(out,labels)
def classifier_libsvm_modular (train_fname=traindat,test_fname=testdat,label_fname=label_traindat,width=2.1,C=1,epsilon=1e-5): from modshogun import RealFeatures, BinaryLabels from modshogun import GaussianKernel, LibSVM, CSVFile feats_train=RealFeatures(CSVFile(train_fname)) feats_test=RealFeatures(CSVFile(test_fname)) labels=BinaryLabels(CSVFile(label_fname)) kernel=GaussianKernel(feats_train, feats_train, width) svm=LibSVM(C, kernel, labels) svm.set_epsilon(epsilon) svm.train() supportvectors = sv_idx=svm.get_support_vectors() alphas=svm.get_alphas() predictions = svm.apply(feats_test) #print predictions.get_labels() return predictions, svm, predictions.get_labels()
def classifier_libsvm_minimal_modular(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
width=2.1,
C=1):
from modshogun import RealFeatures, BinaryLabels
from modshogun import LibSVM, GaussianKernel, CSVFile
from modshogun import ErrorRateMeasure
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = BinaryLabels(CSVFile(label_fname))
kernel = GaussianKernel(feats_train, feats_train, width)
svm = LibSVM(C, kernel, labels)
svm.train()
out = svm.apply(feats_train)
evaluator = ErrorRateMeasure()
testerr = evaluator.evaluate(out, labels)
def classifier_libsvm_modular(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from modshogun import RealFeatures, BinaryLabels
from modshogun import GaussianKernel, LibSVM, CSVFile
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = BinaryLabels(CSVFile(label_fname))
kernel = GaussianKernel(feats_train, feats_train, width)
svm = LibSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
supportvectors = sv_idx = svm.get_support_vectors()
alphas = svm.get_alphas()
predictions = svm.apply(feats_test)
#print predictions.get_labels()
return predictions, svm, predictions.get_labels()
svm = LibSVM(1000.0, gk, labels)
svm.train()
lda=LDA(1,features,labels)
lda.train()
## plot points
subplot(211)
plot(pos[0,:], pos[1,:], "r.")
plot(neg[0,:], neg[1,:], "b.")
grid(True)
title('Data',size=10)
# plot ROC for SVM
subplot(223)
ROC_evaluation=ROCEvaluation()
ROC_evaluation.evaluate(svm.apply(),labels)
roc = ROC_evaluation.get_ROC()
print roc
plot(roc[0], roc[1])
fill_between(roc[0],roc[1],0,alpha=0.1)
text(mean(roc[0])/2,mean(roc[1])/2,'auROC = %.5f' % ROC_evaluation.get_auROC())
grid(True)
xlabel('FPR')
ylabel('TPR')
title('LibSVM (Gaussian kernel, C=%.3f) ROC curve' % svm.get_C1(),size=10)
# plot ROC for LDA
subplot(224)
ROC_evaluation.evaluate(lda.apply(),labels)
roc = ROC_evaluation.get_ROC()
plot(roc[0], roc[1])
svm = LibSVM(1000.0, gk, labels)
svm.train()
lda=LDA(1,features,labels)
lda.train()
## plot points
subplot(211)
plot(pos[0,:], pos[1,:], "r.")
plot(neg[0,:], neg[1,:], "b.")
grid(True)
title('Data',size=10)
# plot PRC for SVM
subplot(223)
PRC_evaluation=PRCEvaluation()
PRC_evaluation.evaluate(svm.apply(),labels)
PRC = PRC_evaluation.get_PRC()
plot(PRC[0], PRC[1])
fill_between(PRC[0],PRC[1],0,alpha=0.1)
text(0.55,mean(PRC[1])/3,'auPRC = %.5f' % PRC_evaluation.get_auPRC())
grid(True)
xlabel('Precision')
ylabel('Recall')
title('LibSVM (Gaussian kernel, C=%.3f) PRC curve' % svm.get_C1(),size=10)
# plot PRC for LDA
subplot(224)
PRC_evaluation.evaluate(lda.apply(),labels)
PRC = PRC_evaluation.get_PRC()
plot(PRC[0], PRC[1])
fill_between(PRC[0],PRC[1],0,alpha=0.1)
tube_epsilon=1e-2
svm=LibSVM()
svm.set_C(C, C)
svm.set_epsilon(epsilon)
svm.set_tube_epsilon(tube_epsilon)
for i in range(3):
data_train=random.rand(num_feats, num_vec)
data_test=random.rand(num_feats, num_vec)
feats_train=RealFeatures(data_train)
feats_test=RealFeatures(data_test)
labels=Labels(random.rand(num_vec).round()*2-1)
svm.set_kernel(LinearKernel(size_cache, scale))
svm.set_labels(labels)
kernel=svm.get_kernel()
print("kernel cache size: %s" % (kernel.get_cache_size()))
kernel.init(feats_test, feats_test)
svm.train()
kernel.init(feats_train, feats_test)
print(svm.apply().get_labels())
#kernel.remove_lhs_and_rhs()
#import pdb
#pdb.set_trace()
