def classifier_svmlight_modular (fm_train_dna=traindat,fm_test_dna=testdat,label_train_dna=label_traindat,C=1.2,epsilon=1e-5,num_threads=1): from shogun.Features import StringCharFeatures, Labels, DNA from shogun.Kernel import WeightedDegreeStringKernel try: from shogun.Classifier import SVMLight except ImportError: print 'No support for SVMLight available.' return feats_train=StringCharFeatures(DNA) feats_train.set_features(fm_train_dna) feats_test=StringCharFeatures(DNA) feats_test.set_features(fm_test_dna) degree=20 kernel=WeightedDegreeStringKernel(feats_train, feats_train, degree) labels=Labels(label_train_dna) svm=SVMLight(C, kernel, labels) svm.set_epsilon(epsilon) svm.parallel.set_num_threads(num_threads) svm.train() kernel.init(feats_train, feats_test) svm.apply().get_labels() return kernel
def classifier_svmlight_linear_term_modular(fm_train_dna=traindna,fm_test_dna=testdna, \
label_train_dna=label_traindna,degree=3, \
C=10,epsilon=1e-5,num_threads=1):
from shogun.Features import StringCharFeatures, Labels, DNA
from shogun.Kernel import WeightedDegreeStringKernel
from shogun.Classifier import SVMLight
feats_train = StringCharFeatures(DNA)
feats_train.set_features(fm_train_dna)
feats_test = StringCharFeatures(DNA)
feats_test.set_features(fm_test_dna)
kernel = WeightedDegreeStringKernel(feats_train, feats_train, degree)
labels = Labels(label_train_dna)
svm = SVMLight(C, kernel, labels)
svm.set_qpsize(3)
svm.set_linear_term(
-numpy.array([1, 2, 3, 4, 5, 6, 7, 8, 7, 6], dtype=numpy.double))
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.train()
kernel.init(feats_train, feats_test)
out = svm.apply().get_labels()
return out, kernel
def classifier_svmlight_linear_term_modular(fm_train_dna=traindna,fm_test_dna=testdna, \
label_train_dna=label_traindna,degree=3, \
C=10,epsilon=1e-5,num_threads=1):
from shogun.Features import StringCharFeatures, BinaryLabels, DNA
from shogun.Kernel import WeightedDegreeStringKernel
from shogun.Classifier import SVMLight
feats_train=StringCharFeatures(DNA)
feats_train.set_features(fm_train_dna)
feats_test=StringCharFeatures(DNA)
feats_test.set_features(fm_test_dna)
kernel=WeightedDegreeStringKernel(feats_train, feats_train, degree)
labels=BinaryLabels(label_train_dna)
svm=SVMLight(C, kernel, labels)
svm.set_qpsize(3)
svm.set_linear_term(-numpy.array([1,2,3,4,5,6,7,8,7,6], dtype=numpy.double));
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.train()
kernel.init(feats_train, feats_test)
out = svm.apply().get_labels()
return out,kernel
def classifier_svmlight_batch_linadd_modular(fm_train_dna, fm_test_dna,
label_train_dna, degree, C,
epsilon, num_threads):
from shogun.Features import StringCharFeatures, Labels, DNA
from shogun.Kernel import WeightedDegreeStringKernel, MSG_DEBUG
try:
from shogun.Classifier import SVMLight
except ImportError:
print 'No support for SVMLight available.'
return
feats_train = StringCharFeatures(DNA)
#feats_train.io.set_loglevel(MSG_DEBUG)
feats_train.set_features(fm_train_dna)
feats_test = StringCharFeatures(DNA)
feats_test.set_features(fm_test_dna)
degree = 20
kernel = WeightedDegreeStringKernel(feats_train, feats_train, degree)
labels = Labels(label_train_dna)
svm = SVMLight(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.train()
kernel.init(feats_train, feats_test)
#print 'SVMLight Objective: %f num_sv: %d' % \
# (svm.get_objective(), svm.get_num_support_vectors())
svm.set_batch_computation_enabled(False)
svm.set_linadd_enabled(False)
svm.apply().get_labels()
svm.set_batch_computation_enabled(True)
labels = svm.apply().get_labels()
return labels, svm
def classifier_svmlight_batch_linadd_modular(fm_train_dna, fm_test_dna,
label_train_dna, degree, C, epsilon, num_threads):
from shogun.Features import StringCharFeatures, BinaryLabels, DNA
from shogun.Kernel import WeightedDegreeStringKernel, MSG_DEBUG
try:
from shogun.Classifier import SVMLight
except ImportError:
print('No support for SVMLight available.')
return
feats_train=StringCharFeatures(DNA)
#feats_train.io.set_loglevel(MSG_DEBUG)
feats_train.set_features(fm_train_dna)
feats_test=StringCharFeatures(DNA)
feats_test.set_features(fm_test_dna)
degree=20
kernel=WeightedDegreeStringKernel(feats_train, feats_train, degree)
labels=BinaryLabels(label_train_dna)
svm=SVMLight(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.train()
kernel.init(feats_train, feats_test)
#print('SVMLight Objective: %f num_sv: %d' % \)
# (svm.get_objective(), svm.get_num_support_vectors())
svm.set_batch_computation_enabled(False)
svm.set_linadd_enabled(False)
svm.apply().get_labels()
svm.set_batch_computation_enabled(True)
labels = svm.apply().get_labels()
return labels, svm
class ShogunPredictor(object):
"""
basic single-task promoter model using string kernels
"""
def __init__(self, degree=4, shifts=32, kernel_cache=10000, cost=1.0):
#TODO: clean up degree
self.degree = degree
self.degree_wdk = degree
self.degree_spectrum = degree
self.shifts = shifts
self.kernel_cache = kernel_cache
self.cost = cost
self.center_offset = 50
self.center_pos = 1200
self.epsilon = 10e-2
self.num_threads = 4
def train(self, data, labels):
kernel = create_promoter_kernel(data, self.center_offset, self.center_pos, self.degree_wdk, self.degree_spectrum, self.shifts, kernel_cache=self.kernel_cache)
print "len(labels) = %i" % (len(labels))
lab = create_labels(labels)
self.svm = SVMLight(self.cost, kernel, lab)
# show debugging output
self.svm.io.enable_progress()
self.svm.io.set_loglevel(MSG_DEBUG)
# optimization settings
num_threads = self.num_threads
self.svm.parallel.set_num_threads(num_threads)
self.svm.set_epsilon(self.epsilon)
self.svm.train()
return self
def predict(self, data):
feat = create_promoter_features(data, self.center_offset, self.center_pos)
out = self.svm.apply(feat).get_values()
return out
def serialization_svmlight_modular(num, dist, width, C):
from shogun.IO import MSG_DEBUG
from shogun.Features import RealFeatures, BinaryLabels, DNA, Alphabet
from shogun.Kernel import WeightedDegreeStringKernel, GaussianKernel
from shogun.Classifier import SVMLight
from numpy import concatenate, ones
from numpy.random import randn, seed
import sys
import types
import random
import bz2
try:
import cPickle as pickle
except ImportError:
import pickle as pickle
import inspect
def save(filename, myobj):
"""
save object to file using pickle
@param filename: name of destination file
@type filename: str
@param myobj: object to save (has to be pickleable)
@type myobj: obj
"""
try:
f = bz2.BZ2File(filename, "wb")
except IOError as details:
sys.stderr.write("File " + filename + " cannot be written\n")
sys.stderr.write(details)
return
pickle.dump(myobj, f, protocol=2)
f.close()
def load(filename):
"""
Load from filename using pickle
@param filename: name of file to load from
@type filename: str
"""
try:
f = bz2.BZ2File(filename, "rb")
except IOError as details:
sys.stderr.write("File " + filename + " cannot be read\n")
sys.stderr.write(details)
return
myobj = pickle.load(f)
f.close()
return myobj
##################################################
# set up toy data and svm
traindata_real = concatenate((randn(2, num) - dist, randn(2, num) + dist), axis=1)
testdata_real = concatenate((randn(2, num) - dist, randn(2, num) + dist), axis=1)
trainlab = concatenate((-ones(num), ones(num)))
testlab = concatenate((-ones(num), ones(num)))
feats_train = RealFeatures(traindata_real)
feats_test = RealFeatures(testdata_real)
kernel = GaussianKernel(feats_train, feats_train, width)
# kernel.io.set_loglevel(MSG_DEBUG)
labels = BinaryLabels(trainlab)
svm = SVMLight(C, kernel, labels)
svm.train()
# svm.io.set_loglevel(MSG_DEBUG)
##################################################
# serialize to file
fn = "serialized_svm.bz2"
# print("serializing SVM to file", fn)
save(fn, svm)
##################################################
# unserialize and sanity check
# print("unserializing SVM")
svm2 = load(fn)
# print("comparing objectives")
svm2.train()
# print("objective before serialization:", svm.get_objective())
# print("objective after serialization:", svm2.get_objective())
# print("comparing predictions")
out = svm.apply(feats_test).get_labels()
out2 = svm2.apply(feats_test).get_labels()
# assert outputs are close
for i in xrange(len(out)):
assert abs(out[i] - out2[i] < 0.000001)
# print("all checks passed.")
return True
def serialization_string_kernels_modular(n_data, num_shifts, size):
"""
serialize svm with string kernels
"""
##################################################
# set up toy data and svm
train_xt, train_lt = generate_random_data(n_data)
test_xt, test_lt = generate_random_data(n_data)
feats_train = construct_features(train_xt)
feats_test = construct_features(test_xt)
max_len = len(train_xt[0])
kernel_wdk = WeightedDegreePositionStringKernel(size, 5)
shifts_vector = numpy.ones(max_len, dtype=numpy.int32) * num_shifts
kernel_wdk.set_shifts(shifts_vector)
########
# set up spectrum
use_sign = False
kernel_spec_1 = WeightedCommWordStringKernel(size, use_sign)
kernel_spec_2 = WeightedCommWordStringKernel(size, use_sign)
########
# combined kernel
kernel = CombinedKernel()
kernel.append_kernel(kernel_wdk)
kernel.append_kernel(kernel_spec_1)
kernel.append_kernel(kernel_spec_2)
# init kernel
labels = BinaryLabels(train_lt)
svm = SVMLight(1.0, kernel, labels)
#svm.io.set_loglevel(MSG_DEBUG)
svm.train(feats_train)
##################################################
# serialize to file
fn = "serialized_svm.bz2"
#print("serializing SVM to file", fn)
save(fn, svm)
##################################################
# unserialize and sanity check
#print("unserializing SVM")
svm2 = load(fn)
#print("comparing predictions")
out = svm.apply(feats_test).get_labels()
out2 = svm2.apply(feats_test).get_labels()
# assert outputs are close
for i in xrange(len(out)):
assert abs(out[i] - out2[i] < 0.000001)
#print("all checks passed.")
return out, out2
def serialization_string_kernels_modular(n_data, num_shifts, size):
"""
serialize svm with string kernels
"""
##################################################
# set up toy data and svm
train_xt, train_lt = generate_random_data(n_data)
test_xt, test_lt = generate_random_data(n_data)
feats_train = construct_features(train_xt)
feats_test = construct_features(test_xt)
max_len = len(train_xt[0])
kernel_wdk = WeightedDegreePositionStringKernel(size, 5)
shifts_vector = numpy.ones(max_len, dtype=numpy.int32)*num_shifts
kernel_wdk.set_shifts(shifts_vector)
########
# set up spectrum
use_sign = False
kernel_spec_1 = WeightedCommWordStringKernel(size, use_sign)
kernel_spec_2 = WeightedCommWordStringKernel(size, use_sign)
########
# combined kernel
kernel = CombinedKernel()
kernel.append_kernel(kernel_wdk)
kernel.append_kernel(kernel_spec_1)
kernel.append_kernel(kernel_spec_2)
# init kernel
labels = BinaryLabels(train_lt);
svm = SVMLight(1.0, kernel, labels)
#svm.io.set_loglevel(MSG_DEBUG)
svm.train(feats_train)
##################################################
# serialize to file
fn = "serialized_svm.bz2"
#print("serializing SVM to file", fn)
save(fn, svm)
##################################################
# unserialize and sanity check
#print("unserializing SVM")
svm2 = load(fn)
#print("comparing predictions")
out = svm.apply(feats_test).get_labels()
out2 = svm2.apply(feats_test).get_labels()
# assert outputs are close
for i in range(len(out)):
assert abs(out[i] - out2[i] < 0.000001)
#print("all checks passed.")
return out,out2
def serialization_svmlight_modular(num, dist, width, C):
from shogun.IO import MSG_DEBUG
from shogun.Features import RealFeatures, BinaryLabels, DNA, Alphabet
from shogun.Kernel import WeightedDegreeStringKernel, GaussianKernel
from shogun.Classifier import SVMLight
from numpy import concatenate, ones
from numpy.random import randn, seed
import sys
import types
import random
import bz2
try:
import cPickle as pickle
except ImportError:
import pickle as pickle
import inspect
def save(filename, myobj):
"""
save object to file using pickle
@param filename: name of destination file
@type filename: str
@param myobj: object to save (has to be pickleable)
@type myobj: obj
"""
try:
f = bz2.BZ2File(filename, 'wb')
except IOError as details:
sys.stderr.write('File ' + filename + ' cannot be written\n')
sys.stderr.write(details)
return
pickle.dump(myobj, f, protocol=2)
f.close()
def load(filename):
"""
Load from filename using pickle
@param filename: name of file to load from
@type filename: str
"""
try:
f = bz2.BZ2File(filename, 'rb')
except IOError as details:
sys.stderr.write('File ' + filename + ' cannot be read\n')
sys.stderr.write(details)
return
myobj = pickle.load(f)
f.close()
return myobj
##################################################
# set up toy data and svm
traindata_real = concatenate((randn(2, num) - dist, randn(2, num) + dist),
axis=1)
testdata_real = concatenate((randn(2, num) - dist, randn(2, num) + dist),
axis=1)
trainlab = concatenate((-ones(num), ones(num)))
testlab = concatenate((-ones(num), ones(num)))
feats_train = RealFeatures(traindata_real)
feats_test = RealFeatures(testdata_real)
kernel = GaussianKernel(feats_train, feats_train, width)
#kernel.io.set_loglevel(MSG_DEBUG)
labels = BinaryLabels(trainlab)
svm = SVMLight(C, kernel, labels)
svm.train()
#svm.io.set_loglevel(MSG_DEBUG)
##################################################
# serialize to file
fn = "serialized_svm.bz2"
print("serializing SVM to file", fn)
save(fn, svm)
##################################################
# unserialize and sanity check
print("unserializing SVM")
svm2 = load(fn)
print("comparing objectives")
svm2.train()
print("objective before serialization:", svm.get_objective())
print("objective after serialization:", svm2.get_objective())
print("comparing predictions")
out = svm.apply(feats_test).get_labels()
out2 = svm2.apply(feats_test).get_labels()
# assert outputs are close
for i in xrange(len(out)):
assert abs(out[i] - out2[i] < 0.000001)
print("all checks passed.")
return True
class ShogunPredictor(object):
"""
basic promoter model using string kernels
"""
def __init__(self, param):
self.param = param
def train(self, data, labels):
"""
model training
"""
# centered WDK/WDK-shift
if self.param["shifts"] == 0:
kernel_center = WeightedDegreeStringKernel(self.param["degree"])
else:
kernel_center = WeightedDegreePositionStringKernel(
10, self.param["degree"])
shifts_vector = numpy.ones(
self.param["center_offset"] * 2,
dtype=numpy.int32) * self.param["shifts"]
kernel_center.set_shifts(shifts_vector)
kernel_center.set_cache_size(self.param["kernel_cache"] / 3)
# border spetrum kernels
size = self.param["kernel_cache"] / 3
use_sign = False
kernel_left = WeightedCommWordStringKernel(size, use_sign)
kernel_right = WeightedCommWordStringKernel(size, use_sign)
# assemble combined kernel
kernel = CombinedKernel()
kernel.append_kernel(kernel_center)
kernel.append_kernel(kernel_left)
kernel.append_kernel(kernel_right)
## building features
feat = create_features(data, self.param["center_offset"],
self.param["center_pos"])
# init combined kernel
kernel.init(feat, feat)
print "len(labels) = %i" % (len(labels))
lab = BinaryLabels(numpy.double(labels))
self.svm = SVMLight(self.param["cost"], kernel, lab)
# show debugging output
self.svm.io.enable_progress()
self.svm.io.set_loglevel(MSG_DEBUG)
# optimization settings
num_threads = 2
self.svm.parallel.set_num_threads(num_threads)
self.svm.set_epsilon(10e-8)
self.svm.train()
return self
def predict(self, data):
"""
model prediction
"""
feat = create_features(data, self.param["center_offset"],
self.param["center_pos"])
out = self.svm.apply(feat).get_values()
return out
class ShogunPredictor(object):
"""
basic promoter model using string kernels
"""
def __init__(self, param):
self.param = param
def train(self, data, labels):
"""
model training
"""
# centered WDK/WDK-shift
if self.param["shifts"] == 0:
kernel_center = WeightedDegreeStringKernel(self.param["degree"])
else:
kernel_center = WeightedDegreePositionStringKernel(10, self.param["degree"])
shifts_vector = numpy.ones(self.param["center_offset"]*2, dtype=numpy.int32)*self.param["shifts"]
kernel_center.set_shifts(shifts_vector)
kernel_center.set_cache_size(self.param["kernel_cache"]/3)
# border spetrum kernels
size = self.param["kernel_cache"]/3
use_sign = False
kernel_left = WeightedCommWordStringKernel(size, use_sign)
kernel_right = WeightedCommWordStringKernel(size, use_sign)
# assemble combined kernel
kernel = CombinedKernel()
kernel.append_kernel(kernel_center)
kernel.append_kernel(kernel_left)
kernel.append_kernel(kernel_right)
## building features
feat = create_features(data, self.param["center_offset"], self.param["center_pos"])
# init combined kernel
kernel.init(feat, feat)
print "len(labels) = %i" % (len(labels))
lab = BinaryLabels(numpy.double(labels))
self.svm = SVMLight(self.param["cost"], kernel, lab)
# show debugging output
self.svm.io.enable_progress()
self.svm.io.set_loglevel(MSG_DEBUG)
# optimization settings
num_threads = 2
self.svm.parallel.set_num_threads(num_threads)
self.svm.set_epsilon(10e-8)
self.svm.train()
return self
def predict(self, data):
"""
model prediction
"""
feat = create_features(data, self.param["center_offset"], self.param["center_pos"])
out = self.svm.apply(feat).get_values()
return out
