def evaluation_cross_validation_mkl_weight_storage(traindat=traindat, label_traindat=label_traindat):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import CrossValidationPrintOutput
from modshogun import CrossValidationMKLStorage
from modshogun import ContingencyTableEvaluation, ACCURACY
from modshogun import StratifiedCrossValidationSplitting
from modshogun import BinaryLabels
from modshogun import RealFeatures, CombinedFeatures
from modshogun import GaussianKernel, CombinedKernel
from modshogun import LibSVM, MKLClassification
from modshogun import Statistics
# training data, combined features all on same data
features=RealFeatures(traindat)
comb_features=CombinedFeatures()
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
labels=BinaryLabels(label_traindat)
# kernel, different Gaussians combined
kernel=CombinedKernel()
kernel.append_kernel(GaussianKernel(10, 0.1))
kernel.append_kernel(GaussianKernel(10, 1))
kernel.append_kernel(GaussianKernel(10, 2))
# create mkl using libsvm, due to a mem-bug, interleaved is not possible
svm=MKLClassification(LibSVM());
svm.set_interleaved_optimization_enabled(False);
svm.set_kernel(kernel);
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy=StratifiedCrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium=ContingencyTableEvaluation(ACCURACY)
# cross-validation instance
cross_validation=CrossValidation(svm, comb_features, labels,
splitting_strategy, evaluation_criterium)
cross_validation.set_autolock(False)
# append cross vlaidation output classes
#cross_validation.add_cross_validation_output(CrossValidationPrintOutput())
mkl_storage=CrossValidationMKLStorage()
cross_validation.add_cross_validation_output(mkl_storage)
cross_validation.set_num_runs(3)
# perform cross-validation
result=cross_validation.evaluate()
# print mkl weights
weights=mkl_storage.get_mkl_weights()
def make_combined_feature (astringv, minseq = 3, maxseq = 8):
from modshogun import CombinedFeatures
feats_train=CombinedFeatures()
raw_feats = []
# initialize the subfeats
for seqlen in range(minseq, maxseq+1):
subkfeats_train=make_string_feature(astringv, start=seqlen-1, order=seqlen)
raw_feats.append(subkfeats_train)
feats_train.append_feature_obj(subkfeats_train)
return feats_train, raw_feats
def construct_features(features):
"""
makes a list
"""
feat_all = [inst for inst in features]
feat_lhs = [inst[0:15] for inst in features]
feat_rhs = [inst[15:] for inst in features]
feat_wd = get_wd_features(feat_all)
feat_spec_1 = get_spectrum_features(feat_lhs, order=3)
feat_spec_2 = get_spectrum_features(feat_rhs, order=3)
feat_comb = CombinedFeatures()
feat_comb.append_feature_obj(feat_wd)
feat_comb.append_feature_obj(feat_spec_1)
feat_comb.append_feature_obj(feat_spec_2)
return feat_comb
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 evaluation_cross_validation_mkl_weight_storage(
traindat=traindat, label_traindat=label_traindat):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import CrossValidationPrintOutput
from modshogun import CrossValidationMKLStorage
from modshogun import ContingencyTableEvaluation, ACCURACY
from modshogun import StratifiedCrossValidationSplitting
from modshogun import BinaryLabels
from modshogun import RealFeatures, CombinedFeatures
from modshogun import GaussianKernel, CombinedKernel
from modshogun import LibSVM, MKLClassification
# training data, combined features all on same data
features = RealFeatures(traindat)
comb_features = CombinedFeatures()
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
labels = BinaryLabels(label_traindat)
# kernel, different Gaussians combined
kernel = CombinedKernel()
kernel.append_kernel(GaussianKernel(10, 0.1))
kernel.append_kernel(GaussianKernel(10, 1))
kernel.append_kernel(GaussianKernel(10, 2))
# create mkl using libsvm, due to a mem-bug, interleaved is not possible
svm = MKLClassification(LibSVM())
svm.set_interleaved_optimization_enabled(False)
svm.set_kernel(kernel)
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy = StratifiedCrossValidationSplitting(labels, 5)
# evaluation method
evaluation_criterium = ContingencyTableEvaluation(ACCURACY)
# cross-validation instance
cross_validation = CrossValidation(svm, comb_features, labels,
splitting_strategy,
evaluation_criterium)
cross_validation.set_autolock(False)
# append cross vlaidation output classes
#cross_validation.add_cross_validation_output(CrossValidationPrintOutput())
mkl_storage = CrossValidationMKLStorage()
cross_validation.add_cross_validation_output(mkl_storage)
cross_validation.set_num_runs(3)
# perform cross-validation
result = cross_validation.evaluate()
# print mkl weights
weights = mkl_storage.get_mkl_weights()
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 construct_features(features):
"""
makes a list
"""
feat_all = [inst for inst in features]
feat_lhs = [inst[0:15] for inst in features]
feat_rhs = [inst[15:] for inst in features]
feat_wd = get_wd_features(feat_all)
feat_spec_1 = get_spectrum_features(feat_lhs, order=3)
feat_spec_2 = get_spectrum_features(feat_rhs, order=3)
feat_comb = CombinedFeatures()
feat_comb.append_feature_obj(feat_wd)
feat_comb.append_feature_obj(feat_spec_1)
feat_comb.append_feature_obj(feat_spec_2)
return feat_comb
def evaluation_cross_validation_multiclass_storage (traindat=traindat, label_traindat=label_traindat):
from modshogun import CrossValidation, CrossValidationResult
from modshogun import CrossValidationPrintOutput
from modshogun import CrossValidationMKLStorage, CrossValidationMulticlassStorage
from modshogun import MulticlassAccuracy, F1Measure
from modshogun import StratifiedCrossValidationSplitting
from modshogun import MulticlassLabels
from modshogun import RealFeatures, CombinedFeatures
from modshogun import GaussianKernel, CombinedKernel
from modshogun import MKLMulticlass
from modshogun import Statistics, MSG_DEBUG, Math
Math.init_random(1)
# training data, combined features all on same data
features=RealFeatures(traindat)
comb_features=CombinedFeatures()
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
comb_features.append_feature_obj(features)
labels=MulticlassLabels(label_traindat)
# kernel, different Gaussians combined
kernel=CombinedKernel()
kernel.append_kernel(GaussianKernel(10, 0.1))
kernel.append_kernel(GaussianKernel(10, 1))
kernel.append_kernel(GaussianKernel(10, 2))
# create mkl using libsvm, due to a mem-bug, interleaved is not possible
svm=MKLMulticlass(1.0,kernel,labels);
svm.set_kernel(kernel);
# splitting strategy for 5 fold cross-validation (for classification its better
# to use "StratifiedCrossValidation", but the standard
# "StratifiedCrossValidationSplitting" is also available
splitting_strategy=StratifiedCrossValidationSplitting(labels, 3)
# evaluation method
evaluation_criterium=MulticlassAccuracy()
# cross-validation instance
cross_validation=CrossValidation(svm, comb_features, labels,
splitting_strategy, evaluation_criterium)
cross_validation.set_autolock(False)
# append cross vlaidation output classes
#cross_validation.add_cross_validation_output(CrossValidationPrintOutput())
#mkl_storage=CrossValidationMKLStorage()
#cross_validation.add_cross_validation_output(mkl_storage)
multiclass_storage=CrossValidationMulticlassStorage()
multiclass_storage.append_binary_evaluation(F1Measure())
cross_validation.add_cross_validation_output(multiclass_storage)
cross_validation.set_num_runs(3)
# perform cross-validation
result=cross_validation.evaluate()
roc_0_0_0 = multiclass_storage.get_fold_ROC(0,0,0)
#print roc_0_0_0
auc_0_0_0 = multiclass_storage.get_fold_evaluation_result(0,0,0,0)
#print auc_0_0_0
return roc_0_0_0, auc_0_0_0
def predict_new_data(graph_file, cons_file, tri_file, other_feature_file):
print 'reading extracted features'
graph_feature = read_feature_data(graph_file)
graph_feature = get_normalized_given_max_min(graph_feature,
'models/grtaph_max_size')
cons_feature = read_feature_data(cons_file)
cons_feature = get_normalized_given_max_min(cons_feature,
'models/cons_max_size')
CC_feature = read_feature_data(tri_file)
CC_feature = get_normalized_given_max_min(CC_feature,
'models/tri_max_size')
ATOS_feature = read_feature_data(other_feature_file)
ATOS_feature = get_normalized_given_max_min(ATOS_feature,
'models/alu_max_size')
width, C, epsilon, num_threads, mkl_epsilon, mkl_norm = 0.5, 1.2, 1e-5, 1, 0.001, 3.5
kernel = CombinedKernel()
feats_train = CombinedFeatures()
feats_test = CombinedFeatures()
#pdb.set_trace()
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(graph_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/graph.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(cons_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/cons.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(CC_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/tri.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(ATOS_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/alu.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
model_file = "models/mkl.dat"
if not os.path.exists(model_file):
print 'downloading model file'
url_add = 'http://rth.dk/resources/mirnasponge/data/mkl.dat'
urllib.urlretrieve(url_add, model_file)
print 'loading trained model'
fstream = SerializableAsciiFile("models/mkl.dat", "r")
new_mkl = MKLClassification()
status = new_mkl.load_serializable(fstream)
print 'model predicting'
kernel.init(feats_train, feats_test)
new_mkl.set_kernel(kernel)
y_out = new_mkl.apply().get_labels()
return y_out
def mkl_multiclass_modular (fm_train_real, fm_test_real, label_train_multiclass, width, C, epsilon, num_threads, mkl_epsilon, mkl_norm): from modshogun import CombinedFeatures, RealFeatures, MulticlassLabels from modshogun import CombinedKernel, GaussianKernel, LinearKernel,PolyKernel from modshogun import MKLMulticlass kernel = CombinedKernel() feats_train = CombinedFeatures() feats_test = CombinedFeatures() subkfeats_train = RealFeatures(fm_train_real) subkfeats_test = RealFeatures(fm_test_real) subkernel = GaussianKernel(10, width) feats_train.append_feature_obj(subkfeats_train) feats_test.append_feature_obj(subkfeats_test) kernel.append_kernel(subkernel) subkfeats_train = RealFeatures(fm_train_real) subkfeats_test = RealFeatures(fm_test_real) subkernel = LinearKernel() feats_train.append_feature_obj(subkfeats_train) feats_test.append_feature_obj(subkfeats_test) kernel.append_kernel(subkernel) subkfeats_train = RealFeatures(fm_train_real) subkfeats_test = RealFeatures(fm_test_real) subkernel = PolyKernel(10,2) feats_train.append_feature_obj(subkfeats_train) feats_test.append_feature_obj(subkfeats_test) kernel.append_kernel(subkernel) kernel.init(feats_train, feats_train) labels = MulticlassLabels(label_train_multiclass) mkl = MKLMulticlass(C, kernel, labels) mkl.set_epsilon(epsilon); mkl.parallel.set_num_threads(num_threads) mkl.set_mkl_epsilon(mkl_epsilon) mkl.set_mkl_norm(mkl_norm) mkl.train() kernel.init(feats_train, feats_test) out = mkl.apply().get_labels() return out
def predict_new_data(graph_file, cons_file, tri_file, other_feature_file):
print "reading extracted features"
graph_feature = read_feature_data(graph_file)
graph_feature = get_normalized_given_max_min(graph_feature, "models/grtaph_max_size")
cons_feature = read_feature_data(cons_file)
cons_feature = get_normalized_given_max_min(cons_feature, "models/cons_max_size")
CC_feature = read_feature_data(tri_file)
CC_feature = get_normalized_given_max_min(CC_feature, "models/tri_max_size")
ATOS_feature = read_feature_data(other_feature_file)
ATOS_feature = get_normalized_given_max_min(ATOS_feature, "models/alu_max_size")
width, C, epsilon, num_threads, mkl_epsilon, mkl_norm = 0.5, 1.2, 1e-5, 1, 0.001, 3.5
kernel = CombinedKernel()
feats_train = CombinedFeatures()
feats_test = CombinedFeatures()
# pdb.set_trace()
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(graph_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/graph.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(cons_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/cons.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(CC_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/tri.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(ATOS_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/alu.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
model_file = "models/mkl.dat"
if not os.path.exists(model_file):
print "downloading model file"
url_add = "http://rth.dk/resources/mirnasponge/data/mkl.dat"
urllib.urlretrieve(url_add, model_file)
print "loading trained model"
fstream = SerializableAsciiFile("models/mkl.dat", "r")
new_mkl = MKLClassification()
status = new_mkl.load_serializable(fstream)
print "model predicting"
kernel.init(feats_train, feats_test)
new_mkl.set_kernel(kernel)
y_out = new_mkl.apply().get_labels()
return y_out
def runShogunSVMMultipleKernels(train_xt, train_lt, test_xt):
"""
Run SVM with Multiple Kernels
"""
##################################################
# Take all examples
idxs = np.random.randint(1, 14000, 14000)
train_xt = np.array(train_xt)[idxs]
train_lt = np.array(train_lt)[idxs]
# Initialize kernel and features
kernel = CombinedKernel()
feats_train = CombinedFeatures()
feats_test = CombinedFeatures()
labels = BinaryLabels(train_lt)
##################### Multiple Spectrum Kernels #########################
for i in range(K1, K2, -1):
# append training data to combined feature object
charfeat_train = StringCharFeatures(list(train_xt), DNA)
feats_train_k1 = StringWordFeatures(DNA)
feats_train_k1.obtain_from_char(charfeat_train, i - 1, i, GAP, False)
preproc = SortWordString()
preproc.init(feats_train_k1)
feats_train_k1.add_preprocessor(preproc)
feats_train_k1.apply_preprocessor()
# append testing data to combined feature object
charfeat_test = StringCharFeatures(test_xt, DNA)
feats_test_k1 = StringWordFeatures(DNA)
feats_test_k1.obtain_from_char(charfeat_test, i - 1, i, GAP, False)
feats_test_k1.add_preprocessor(preproc)
feats_test_k1.apply_preprocessor()
# append features
feats_train.append_feature_obj(charfeat_train)
feats_test.append_feature_obj(charfeat_test)
# append spectrum kernel
kernel1 = CommWordStringKernel(10, i)
kernel1.io.set_loglevel(MSG_DEBUG)
kernel.append_kernel(kernel1)
'''
Uncomment this for Multiple Weighted degree kernels and comment
the multiple spectrum kernel block above instead
##################### Multiple Weighted Degree Kernel #########################
for i in range(K1,K2,-1):
# append training data to combined feature object
charfeat_train = StringCharFeatures(list(train_xt), DNA)
# append testing data to combined feature object
charfeat_test = StringCharFeatures(test_xt, DNA)
# append features
feats_train.append_feature_obj(charfeat_train);
feats_test.append_feature_obj(charfeat_test);
# setup weighted degree kernel
kernel1=WeightedDegreePositionStringKernel(10,i);
kernel1.io.set_loglevel(MSG_DEBUG);
kernel1.set_shifts(SHIFT*np.ones(len(train_xt[0]), dtype=np.int32))
kernel1.set_position_weights(np.ones(len(train_xt[0]), dtype=np.float64));
kernel.append_kernel(kernel1);
'''
##################### Training #########################
print "Starting MKL training.."
mkl = MKLClassification()
mkl.set_mkl_norm(3) #1,2,3
mkl.set_C(SVMC, SVMC)
mkl.set_kernel(kernel)
mkl.set_labels(labels)
mkl.train(feats_train)
print "Making predictions!"
out1 = mkl.apply(feats_train).get_labels()
out2 = mkl.apply(feats_test).get_labels()
return out1, out2, train_lt
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
def mkl(train_features,
train_labels,
test_features,
test_labels,
width=5,
C=1.2,
epsilon=1e-2,
mkl_epsilon=0.001,
mkl_norm=2):
from modshogun import CombinedKernel, CombinedFeatures
from modshogun import GaussianKernel, LinearKernel, PolyKernel
from modshogun import MKLMulticlass, MulticlassAccuracy
kernel = CombinedKernel()
feats_train = CombinedFeatures()
feats_test = CombinedFeatures()
feats_train.append_feature_obj(train_features)
feats_test.append_feature_obj(test_features)
subkernel = GaussianKernel(10, width)
kernel.append_kernel(subkernel)
feats_train.append_feature_obj(train_features)
feats_test.append_feature_obj(test_features)
subkernel = LinearKernel()
kernel.append_kernel(subkernel)
feats_train.append_feature_obj(train_features)
feats_test.append_feature_obj(test_features)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_train)
mkl = MKLMulticlass(C, kernel, train_labels)
mkl.set_epsilon(epsilon)
mkl.set_mkl_epsilon(mkl_epsilon)
mkl.set_mkl_norm(mkl_norm)
mkl.train()
train_output = mkl.apply()
kernel.init(feats_train, feats_test)
test_output = mkl.apply()
evaluator = MulticlassAccuracy()
print 'MKL training error is %.4f' % (
(1 - evaluator.evaluate(train_output, train_labels)) * 100)
print 'MKL test error is %.4f' % (
(1 - evaluator.evaluate(test_output, test_labels)) * 100)
def kernel_combined_modular (fm_train_real=traindat,fm_test_real=testdat,fm_train_dna=traindna,fm_test_dna=testdna ): from modshogun import CombinedKernel, GaussianKernel, FixedDegreeStringKernel, LocalAlignmentStringKernel from modshogun import RealFeatures, StringCharFeatures, CombinedFeatures, DNA kernel=CombinedKernel() feats_train=CombinedFeatures() feats_test=CombinedFeatures() subkfeats_train=RealFeatures(fm_train_real) subkfeats_test=RealFeatures(fm_test_real) subkernel=GaussianKernel(10, 1.1) feats_train.append_feature_obj(subkfeats_train) feats_test.append_feature_obj(subkfeats_test) kernel.append_kernel(subkernel) subkfeats_train=StringCharFeatures(fm_train_dna, DNA) subkfeats_test=StringCharFeatures(fm_test_dna, DNA) degree=3 subkernel=FixedDegreeStringKernel(10, degree) feats_train.append_feature_obj(subkfeats_train) feats_test.append_feature_obj(subkfeats_test) kernel.append_kernel(subkernel) subkfeats_train=StringCharFeatures(fm_train_dna, DNA) subkfeats_test=StringCharFeatures(fm_test_dna, DNA) subkernel=LocalAlignmentStringKernel(10) feats_train.append_feature_obj(subkfeats_train) feats_test.append_feature_obj(subkfeats_test) kernel.append_kernel(subkernel) kernel.init(feats_train, feats_train) 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 mkl(train_features, train_labels, test_features, test_labels, width=5, C=1.2, epsilon=1e-2, mkl_epsilon=0.001, mkl_norm=2): from modshogun import CombinedKernel, CombinedFeatures from modshogun import GaussianKernel, LinearKernel, PolyKernel from modshogun import MKLMulticlass, MulticlassAccuracy kernel = CombinedKernel() feats_train = CombinedFeatures() feats_test = CombinedFeatures() feats_train.append_feature_obj(train_features) feats_test.append_feature_obj(test_features) subkernel = GaussianKernel(10,width) kernel.append_kernel(subkernel) feats_train.append_feature_obj(train_features) feats_test.append_feature_obj(test_features) subkernel = LinearKernel() kernel.append_kernel(subkernel) feats_train.append_feature_obj(train_features) feats_test.append_feature_obj(test_features) subkernel = PolyKernel(10,2) kernel.append_kernel(subkernel) kernel.init(feats_train, feats_train) mkl = MKLMulticlass(C, kernel, train_labels) mkl.set_epsilon(epsilon); mkl.set_mkl_epsilon(mkl_epsilon) mkl.set_mkl_norm(mkl_norm) mkl.train() train_output = mkl.apply() kernel.init(feats_train, feats_test) test_output = mkl.apply() evaluator = MulticlassAccuracy() print 'MKL training error is %.4f' % ((1-evaluator.evaluate(train_output, train_labels))*100) print 'MKL test error is %.4f' % ((1-evaluator.evaluate(test_output, test_labels))*100)
def runShogunSVMMultipleKernels(train_xt, train_lt, test_xt):
"""
Run SVM with Multiple Kernels
"""
##################################################
# Take all examples
idxs = np.random.randint(1,14000,14000);
train_xt = np.array(train_xt)[idxs];
train_lt = np.array(train_lt)[idxs];
# Initialize kernel and features
kernel=CombinedKernel()
feats_train=CombinedFeatures()
feats_test=CombinedFeatures()
labels = BinaryLabels(train_lt)
##################### Multiple Spectrum Kernels #########################
for i in range(K1,K2,-1):
# append training data to combined feature object
charfeat_train = StringCharFeatures(list(train_xt), DNA)
feats_train_k1 = StringWordFeatures(DNA)
feats_train_k1.obtain_from_char(charfeat_train, i-1, i, GAP, False)
preproc=SortWordString()
preproc.init(feats_train_k1)
feats_train_k1.add_preprocessor(preproc)
feats_train_k1.apply_preprocessor()
# append testing data to combined feature object
charfeat_test = StringCharFeatures(test_xt, DNA)
feats_test_k1=StringWordFeatures(DNA)
feats_test_k1.obtain_from_char(charfeat_test, i-1, i, GAP, False)
feats_test_k1.add_preprocessor(preproc)
feats_test_k1.apply_preprocessor()
# append features
feats_train.append_feature_obj(charfeat_train);
feats_test.append_feature_obj(charfeat_test);
# append spectrum kernel
kernel1=CommWordStringKernel(10,i);
kernel1.io.set_loglevel(MSG_DEBUG);
kernel.append_kernel(kernel1);
'''
Uncomment this for Multiple Weighted degree kernels and comment
the multiple spectrum kernel block above instead
##################### Multiple Weighted Degree Kernel #########################
for i in range(K1,K2,-1):
# append training data to combined feature object
charfeat_train = StringCharFeatures(list(train_xt), DNA)
# append testing data to combined feature object
charfeat_test = StringCharFeatures(test_xt, DNA)
# append features
feats_train.append_feature_obj(charfeat_train);
feats_test.append_feature_obj(charfeat_test);
# setup weighted degree kernel
kernel1=WeightedDegreePositionStringKernel(10,i);
kernel1.io.set_loglevel(MSG_DEBUG);
kernel1.set_shifts(SHIFT*np.ones(len(train_xt[0]), dtype=np.int32))
kernel1.set_position_weights(np.ones(len(train_xt[0]), dtype=np.float64));
kernel.append_kernel(kernel1);
'''
##################### Training #########################
print "Starting MKL training.."
mkl = MKLClassification();
mkl.set_mkl_norm(3) #1,2,3
mkl.set_C(SVMC, SVMC)
mkl.set_kernel(kernel)
mkl.set_labels(labels)
mkl.train(feats_train)
print "Making predictions!"
out1 = mkl.apply(feats_train).get_labels();
out2 = mkl.apply(feats_test).get_labels();
return out1,out2,train_lt
