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_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 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 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 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
