def kernel_fisher_modular(fm_train_dna=traindat, fm_test_dna=testdat, label_train_dna=label_traindat, N=1, M=4, pseudo=1e-1, order=1, gap=0, reverse=False, kargs=[1, False, True]): from modshogun import StringCharFeatures, StringWordFeatures, FKFeatures, DNA from modshogun import PolyKernel from modshogun import HMM, BW_NORMAL #, MSG_DEBUG # train HMM for positive class charfeat = StringCharFeatures(fm_hmm_pos, DNA) #charfeat.io.set_loglevel(MSG_DEBUG) hmm_pos_train = StringWordFeatures(charfeat.get_alphabet()) hmm_pos_train.obtain_from_char(charfeat, order - 1, order, gap, reverse) pos = HMM(hmm_pos_train, N, M, pseudo) pos.baum_welch_viterbi_train(BW_NORMAL) # train HMM for negative class charfeat = StringCharFeatures(fm_hmm_neg, DNA) hmm_neg_train = StringWordFeatures(charfeat.get_alphabet()) hmm_neg_train.obtain_from_char(charfeat, order - 1, order, gap, reverse) neg = HMM(hmm_neg_train, N, M, pseudo) neg.baum_welch_viterbi_train(BW_NORMAL) # Kernel training data charfeat = StringCharFeatures(fm_train_dna, DNA) wordfeats_train = StringWordFeatures(charfeat.get_alphabet()) wordfeats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse) # Kernel testing data charfeat = StringCharFeatures(fm_test_dna, DNA) wordfeats_test = StringWordFeatures(charfeat.get_alphabet()) wordfeats_test.obtain_from_char(charfeat, order - 1, order, gap, reverse) # get kernel on training data pos.set_observations(wordfeats_train) neg.set_observations(wordfeats_train) feats_train = FKFeatures(10, pos, neg) feats_train.set_opt_a(-1) #estimate prior kernel = PolyKernel(feats_train, feats_train, *kargs) km_train = kernel.get_kernel_matrix() # get kernel on testing data pos_clone = HMM(pos) neg_clone = HMM(neg) pos_clone.set_observations(wordfeats_test) neg_clone.set_observations(wordfeats_test) feats_test = FKFeatures(10, pos_clone, neg_clone) feats_test.set_a(feats_train.get_a()) #use prior from training data kernel.init(feats_train, feats_test) km_test = kernel.get_kernel_matrix() return km_train, km_test, kernel
def kernel_top_modular(fm_train_dna=traindat, fm_test_dna=testdat, label_train_dna=label_traindat, pseudo=1e-1, order=1, gap=0, reverse=False, kargs=[1, False, True]): from modshogun import StringCharFeatures, StringWordFeatures, TOPFeatures, DNA from modshogun import PolyKernel from modshogun import HMM, BW_NORMAL N = 1 # toy HMM with 1 state M = 4 # 4 observations -> DNA # train HMM for positive class charfeat = StringCharFeatures(fm_hmm_pos, DNA) hmm_pos_train = StringWordFeatures(charfeat.get_alphabet()) hmm_pos_train.obtain_from_char(charfeat, order - 1, order, gap, reverse) pos = HMM(hmm_pos_train, N, M, pseudo) pos.baum_welch_viterbi_train(BW_NORMAL) # train HMM for negative class charfeat = StringCharFeatures(fm_hmm_neg, DNA) hmm_neg_train = StringWordFeatures(charfeat.get_alphabet()) hmm_neg_train.obtain_from_char(charfeat, order - 1, order, gap, reverse) neg = HMM(hmm_neg_train, N, M, pseudo) neg.baum_welch_viterbi_train(BW_NORMAL) # Kernel training data charfeat = StringCharFeatures(fm_train_dna, DNA) wordfeats_train = StringWordFeatures(charfeat.get_alphabet()) wordfeats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse) # Kernel testing data charfeat = StringCharFeatures(fm_test_dna, DNA) wordfeats_test = StringWordFeatures(charfeat.get_alphabet()) wordfeats_test.obtain_from_char(charfeat, order - 1, order, gap, reverse) # get kernel on training data pos.set_observations(wordfeats_train) neg.set_observations(wordfeats_train) feats_train = TOPFeatures(10, pos, neg, False, False) kernel = PolyKernel(feats_train, feats_train, *kargs) km_train = kernel.get_kernel_matrix() # get kernel on testing data pos_clone = HMM(pos) neg_clone = HMM(neg) pos_clone.set_observations(wordfeats_test) neg_clone.set_observations(wordfeats_test) feats_test = TOPFeatures(10, pos_clone, neg_clone, False, False) kernel.init(feats_train, feats_test) km_test = kernel.get_kernel_matrix() return km_train, km_test, kernel
def kernel_fisher_modular (fm_train_dna=traindat, fm_test_dna=testdat, label_train_dna=label_traindat, N=1,M=4,pseudo=1e-1,order=1,gap=0,reverse=False, kargs=[1,False,True]): from modshogun import StringCharFeatures, StringWordFeatures, FKFeatures, DNA from modshogun import PolyKernel from modshogun import HMM, BW_NORMAL#, MSG_DEBUG # train HMM for positive class charfeat=StringCharFeatures(fm_hmm_pos, DNA) #charfeat.io.set_loglevel(MSG_DEBUG) hmm_pos_train=StringWordFeatures(charfeat.get_alphabet()) hmm_pos_train.obtain_from_char(charfeat, order-1, order, gap, reverse) pos=HMM(hmm_pos_train, N, M, pseudo) pos.baum_welch_viterbi_train(BW_NORMAL) # train HMM for negative class charfeat=StringCharFeatures(fm_hmm_neg, DNA) hmm_neg_train=StringWordFeatures(charfeat.get_alphabet()) hmm_neg_train.obtain_from_char(charfeat, order-1, order, gap, reverse) neg=HMM(hmm_neg_train, N, M, pseudo) neg.baum_welch_viterbi_train(BW_NORMAL) # Kernel training data charfeat=StringCharFeatures(fm_train_dna, DNA) wordfeats_train=StringWordFeatures(charfeat.get_alphabet()) wordfeats_train.obtain_from_char(charfeat, order-1, order, gap, reverse) # Kernel testing data charfeat=StringCharFeatures(fm_test_dna, DNA) wordfeats_test=StringWordFeatures(charfeat.get_alphabet()) wordfeats_test.obtain_from_char(charfeat, order-1, order, gap, reverse) # get kernel on training data pos.set_observations(wordfeats_train) neg.set_observations(wordfeats_train) feats_train=FKFeatures(10, pos, neg) feats_train.set_opt_a(-1) #estimate prior kernel=PolyKernel(feats_train, feats_train, *kargs) km_train=kernel.get_kernel_matrix() # get kernel on testing data pos_clone=HMM(pos) neg_clone=HMM(neg) pos_clone.set_observations(wordfeats_test) neg_clone.set_observations(wordfeats_test) feats_test=FKFeatures(10, pos_clone, neg_clone) feats_test.set_a(feats_train.get_a()) #use prior from training data kernel.init(feats_train, feats_test) km_test=kernel.get_kernel_matrix() return km_train,km_test,kernel
def kernel_top_modular (fm_train_dna=traindat,fm_test_dna=testdat,label_train_dna=label_traindat,pseudo=1e-1, order=1,gap=0,reverse=False,kargs=[1, False, True]): from modshogun import StringCharFeatures, StringWordFeatures, TOPFeatures, DNA from modshogun import PolyKernel from modshogun import HMM, BW_NORMAL N=1 # toy HMM with 1 state M=4 # 4 observations -> DNA # train HMM for positive class charfeat=StringCharFeatures(fm_hmm_pos, DNA) hmm_pos_train=StringWordFeatures(charfeat.get_alphabet()) hmm_pos_train.obtain_from_char(charfeat, order-1, order, gap, reverse) pos=HMM(hmm_pos_train, N, M, pseudo) pos.baum_welch_viterbi_train(BW_NORMAL) # train HMM for negative class charfeat=StringCharFeatures(fm_hmm_neg, DNA) hmm_neg_train=StringWordFeatures(charfeat.get_alphabet()) hmm_neg_train.obtain_from_char(charfeat, order-1, order, gap, reverse) neg=HMM(hmm_neg_train, N, M, pseudo) neg.baum_welch_viterbi_train(BW_NORMAL) # Kernel training data charfeat=StringCharFeatures(fm_train_dna, DNA) wordfeats_train=StringWordFeatures(charfeat.get_alphabet()) wordfeats_train.obtain_from_char(charfeat, order-1, order, gap, reverse) # Kernel testing data charfeat=StringCharFeatures(fm_test_dna, DNA) wordfeats_test=StringWordFeatures(charfeat.get_alphabet()) wordfeats_test.obtain_from_char(charfeat, order-1, order, gap, reverse) # get kernel on training data pos.set_observations(wordfeats_train) neg.set_observations(wordfeats_train) feats_train=TOPFeatures(10, pos, neg, False, False) kernel=PolyKernel(feats_train, feats_train, *kargs) km_train=kernel.get_kernel_matrix() # get kernel on testing data pos_clone=HMM(pos) neg_clone=HMM(neg) pos_clone.set_observations(wordfeats_test) neg_clone.set_observations(wordfeats_test) feats_test=TOPFeatures(10, pos_clone, neg_clone, False, False) kernel.init(feats_train, feats_test) km_test=kernel.get_kernel_matrix() return km_train,km_test,kernel
def kernel_poly_modular (train_fname=traindat,test_fname=testdat,degree=4,inhomogene=False, use_normalization=True): from modshogun import RealFeatures, PolyKernel, CSVFile feats_train=RealFeatures(CSVFile(train_fname)) feats_test=RealFeatures(CSVFile(test_fname)) kernel=PolyKernel( feats_train, feats_train, degree, inhomogene, use_normalization) 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_poly_modular(train_fname=traindat, test_fname=testdat, degree=4, inhomogene=False, use_normalization=True): from modshogun import RealFeatures, PolyKernel, CSVFile feats_train = RealFeatures(CSVFile(train_fname)) feats_test = RealFeatures(CSVFile(test_fname)) kernel = PolyKernel(feats_train, feats_train, degree, inhomogene, use_normalization) 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_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_sparse_poly_modular (fm_train_real=traindat,fm_test_real=testdat, size_cache=10,degree=3,inhomogene=True ): from modshogun import SparseRealFeatures from modshogun import PolyKernel feats_train=SparseRealFeatures(fm_train_real) feats_test=SparseRealFeatures(fm_test_real) kernel=PolyKernel(feats_train, feats_train, size_cache, degree, inhomogene) 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_sparse_poly_modular (fm_train_real=traindat,fm_test_real=testdat, size_cache=10,degree=3,inhomogene=True ): from modshogun import SparseRealFeatures from modshogun import PolyKernel feats_train=SparseRealFeatures(fm_train_real) feats_test=SparseRealFeatures(fm_test_real) kernel=PolyKernel(feats_train, feats_train, size_cache, inhomogene, degree) 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_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 mkl_binclass_modular (fm_train_real=traindat,fm_test_real=testdat,fm_label_twoclass = label_traindat): ################################## # set up and train # create some poly train/test matrix tfeats = RealFeatures(fm_train_real) tkernel = PolyKernel(10,3) tkernel.init(tfeats, tfeats) K_train = tkernel.get_kernel_matrix() pfeats = RealFeatures(fm_test_real) tkernel.init(tfeats, pfeats) K_test = tkernel.get_kernel_matrix() # create combined train features feats_train = CombinedFeatures() feats_train.append_feature_obj(RealFeatures(fm_train_real)) # and corresponding combined kernel kernel = CombinedKernel() kernel.append_kernel(CustomKernel(K_train)) kernel.append_kernel(PolyKernel(10,2)) kernel.init(feats_train, feats_train) # train mkl labels = BinaryLabels(fm_label_twoclass) mkl = MKLClassification() # which norm to use for MKL mkl.set_mkl_norm(1) #2,3 # set cost (neg, pos) mkl.set_C(1, 1) # set kernel and labels mkl.set_kernel(kernel) mkl.set_labels(labels) # train mkl.train() #w=kernel.get_subkernel_weights() #kernel.set_subkernel_weights(w) ################################## # test # create combined test features feats_pred = CombinedFeatures() feats_pred.append_feature_obj(RealFeatures(fm_test_real)) # and corresponding combined kernel kernel = CombinedKernel() kernel.append_kernel(CustomKernel(K_test)) kernel.append_kernel(PolyKernel(10, 2)) kernel.init(feats_train, feats_pred) # and classify mkl.set_kernel(kernel) mkl.apply() return mkl.apply(),kernel