def _union_train(self, prepared_data, param):
"""
perform inner training by processing the tree
"""
normalizer = MultitaskKernelNormalizer(prepared_data.task_vector_nums)
# set similarity
for task_name_lhs in prepared_data.get_task_names():
for task_name_rhs in prepared_data.get_task_names():
similarity = 1.0
normalizer.set_task_similarity(
prepared_data.name_to_id(task_name_lhs),
prepared_data.name_to_id(task_name_rhs), similarity)
lab = shogun_factory.create_labels(prepared_data.labels)
print "creating empty kernel"
kernel = shogun_factory.create_kernel(prepared_data.examples, param)
print "setting normalizer"
kernel.set_normalizer(normalizer)
kernel.init_normalizer()
svm = shogun_factory.create_svm(param, kernel, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
# train SVM
svm.train()
return svm
def _union_train(self, prepared_data, param):
"""
perform inner training by processing the tree
"""
normalizer = MultitaskKernelNormalizer(prepared_data.task_vector_nums)
# set similarity
for task_name_lhs in prepared_data.get_task_names():
for task_name_rhs in prepared_data.get_task_names():
similarity = 1.0
normalizer.set_task_similarity(prepared_data.name_to_id(task_name_lhs), prepared_data.name_to_id(task_name_rhs), similarity)
lab = shogun_factory.create_labels(prepared_data.labels)
print "creating empty kernel"
kernel = shogun_factory.create_kernel(prepared_data.examples, param)
print "setting normalizer"
kernel.set_normalizer(normalizer)
kernel.init_normalizer()
svm = shogun_factory.create_svm(param, kernel, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
# train SVM
svm.train()
return svm
def create_normalizer_from_taxonomy(taxonomy):
"""
creates kernel normalizer with similarities set
from hop-distance according to taxnomoy
"""
#TODO fix --> num tasks can be computed from leaves etc...
# fetch taxonomy
# taxonomy = param.taxonomy.data
print "WARNING; HARDCODED DISTANCE MATRIX IN HERE"
hardcoded_distances = helper.load("/fml/ag-raetsch/home/cwidmer/svn/projects/alt_splice_code/src/task_sim_tis.bz2")
# set normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
# compute distances
distances = numpy.zeros((data.get_num_tasks(), data.get_num_tasks()))
similarities = numpy.zeros((data.get_num_tasks(), data.get_num_tasks()))
for (i,task_name_lhs) in enumerate(data.get_task_names()):
for (j, task_name_rhs) in enumerate(data.get_task_names()):
distances[i,j] = task_similarities.compute_hop_distance(taxonomy, task_name_lhs, task_name_rhs)
# normalize distances
distances = distances / numpy.max(distances)
# set similarity
for (i, task_name_lhs) in enumerate(data.get_task_names()):
for (j, task_name_rhs) in enumerate(data.get_task_names()):
similarity = param.base_similarity - distances[i,j]
normalizer.set_task_similarity(i, j, similarity)
# save for later
similarities[i,j] = similarity
return normalizer
def _inner_train(self, prepared_data, param):
"""
perform inner training by processing the tree
"""
# init seq handler
classifiers = []
#################
# mtk
normalizer = MultitaskKernelNormalizer(prepared_data.task_vector_nums)
from method_mhc_rbf import SequencesHandlerRbf
task_kernel = SequencesHandlerRbf(1, param.base_similarity, prepared_data.get_task_names(), param.flags["wdk_rbf_on"])
# set similarity
for task_name_lhs in prepared_data.get_task_names():
for task_name_rhs in prepared_data.get_task_names():
similarity = task_kernel.get_similarity(task_name_lhs, task_name_rhs)
normalizer.set_task_similarity(prepared_data.name_to_id(task_name_lhs), prepared_data.name_to_id(task_name_rhs), similarity)
lab = shogun_factory.create_labels(prepared_data.labels)
print "creating empty kernel"
kernel = shogun_factory.create_kernel(prepared_data.examples, param)
print "setting normalizer"
kernel.set_normalizer(normalizer)
kernel.init_normalizer()
svm = shogun_factory.create_svm(param, kernel, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
# train SVM
svm.train()
classifiers.append(svm)
#################
# dirac
#import pdb
#pdb.set_trace()
svm_dirac = self._dirac_train(prepared_data, param)
classifiers.append(svm_dirac)
##
#union
#svm_union = self._union_train(prepared_data, param)
#classifiers.append(svm_union)
return classifiers
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
# merge data sets
data = PreparedMultitaskData(train_data, shuffle=False)
# create shogun data objects
base_wdk = shogun_factory.create_kernel(data.examples, param)
lab = shogun_factory.create_labels(data.labels)
# set normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
########################################################
print "creating a kernel for each node:"
########################################################
# init seq handler
task_kernel = SequencesHandlerRbf(1, param.base_similarity,
data.get_task_names(),
param.flags["wdk_rbf_on"])
similarities = numpy.zeros(
(data.get_num_tasks(), data.get_num_tasks()))
# convert distance to similarity
for task_name_lhs in data.get_task_names():
for task_name_rhs in data.get_task_names():
# convert similarity with simple transformation
similarity = task_kernel.get_similarity(
task_name_lhs, task_name_rhs)
print similarity
print "similarity (%s,%s)=%f" % (task_name_lhs, task_name_rhs,
similarity)
normalizer.set_task_similarity(data.name_to_id(task_name_lhs),
data.name_to_id(task_name_rhs),
similarity)
# save for later
similarities[data.name_to_id(task_name_lhs),
data.name_to_id(task_name_rhs)] = similarity
# set normalizer
base_wdk.set_normalizer(normalizer)
base_wdk.init_normalizer()
# set up svm
svm = SVMLight(param.cost, base_wdk, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
# normalize cost
norm_c_pos = param.cost / float(len([l
for l in data.labels if l == 1]))
norm_c_neg = param.cost / float(
len([l for l in data.labels if l == -1]))
svm.set_C(norm_c_neg, norm_c_pos)
# start training
svm.train()
# save additional information
self.additional_information["svm objective"] = svm.get_objective()
self.additional_information["num sv"] = svm.get_num_support_vectors()
#self.additional_information["distances"] = distances
self.additional_information["similarities"] = similarities
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in data.get_task_names():
task_num = data.name_to_id(task_name)
# save svm and task_num
svms[task_name] = (task_num, param, svm)
return svms
def _inner_train(self, prepared_data, param):
"""
perform inner training by processing the tree
"""
# init seq handler
pseudoseqs = SequencesHandler()
classifiers = []
for pocket in self.get_pockets(param.flags["all_positions"]):
print "creating normalizer"
#import pdb
#pdb.set_trace()
normalizer = MultitaskKernelNormalizer(prepared_data.task_vector_nums)
from method_mhc_rbf import SequencesHandlerRbf
task_kernel = SequencesHandlerRbf(1, param.base_similarity, prepared_data.get_task_names(), param.flags["wdk_rbf_on"])
print "processing pocket", pocket
M = prepared_data.get_num_tasks()
save_sim_p = numpy.zeros((M,M))
save_sim_t = numpy.zeros((M,M))
# set similarity
for task_name_lhs in prepared_data.get_task_names():
for task_name_rhs in prepared_data.get_task_names():
similarity = 0.0
for pseudo_seq_pos in pocket:
similarity += float(pseudoseqs.get_similarity(task_name_lhs, task_name_rhs, pseudo_seq_pos-1))
# normalize
similarity = similarity / float(len(pocket))
similarity_task = task_kernel.get_similarity(task_name_lhs, task_name_rhs)
print "pocket %s (%s, %s) = %f" % (str(pocket), task_name_lhs, task_name_rhs, similarity)
normalizer.set_task_similarity(prepared_data.name_to_id(task_name_lhs), prepared_data.name_to_id(task_name_rhs), similarity)
save_sim_p[prepared_data.name_to_id(task_name_lhs), prepared_data.name_to_id(task_name_rhs)] = similarity
save_sim_t[prepared_data.name_to_id(task_name_lhs), prepared_data.name_to_id(task_name_rhs)] = similarity_task
#from IPython.Shell import IPShellEmbed
#IPShellEmbed([])()
lab = shogun_factory.create_labels(prepared_data.labels)
print "creating empty kernel"
kernel = shogun_factory.create_kernel(prepared_data.examples, param)
print "setting normalizer"
kernel.set_normalizer(normalizer)
kernel.init_normalizer()
print "training SVM for pocket", pocket
svm = shogun_factory.create_svm(param, kernel, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
# train SVM
svm.train()
#import pdb
#pdb.set_trace()
classifiers.append(svm)
return classifiers
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
# merge data sets
data = PreparedMultitaskData(train_data, shuffle=True)
# create shogun label
lab = shogun_factory.create_labels(data.labels)
##################################################
# define pockets
##################################################
pockets = [0] * 9
pockets[0] = [1, 5, 6, 7, 8, 31, 32, 33, 34]
pockets[1] = [1, 2, 3, 4, 6, 7, 8, 9, 11, 21, 31]
pockets[2] = [11, 20, 21, 22, 29, 31]
pockets[3] = [8, 30, 31, 32]
pockets[4] = [10, 11, 30]
pockets[5] = [10, 11, 12, 13, 20, 29]
pockets[6] = [10, 12, 20, 22, 26, 27, 28, 29]
pockets[7] = [12, 14, 15, 26]
pockets[8] = [13, 15, 16, 17, 18, 19, 20, 23, 24, 25, 26]
#new_pockets = []
# merge neighboring pockets
#for i in range(8):
# new_pockets.append(list(set(pockets[i]).union(set(pockets[i+1]))))
#pockets = new_pockets
########################################################
print "creating a kernel:"
########################################################
# assemble combined kernel
combined_kernel = CombinedKernel()
combined_kernel.io.set_loglevel(shogun.Kernel.MSG_INFO)
base_features = shogun_factory.create_features(data.examples)
combined_features = CombinedFeatures()
##################################################
# intra-domain blocks
# intra_block_vec = PairiiVec()
#
# for task_id in data.get_task_ids():
# intra_block_vec.push_back(Pairii(task_id, task_id))
#
#
#
# # create mask-based normalizer
# normalizer = MultitaskKernelMaskPairNormalizer(data.task_vector_nums, intra_block_vec)
# kernel = shogun_factory.create_empty_kernel(param)
# kernel.set_normalizer(normalizer)
#
# # append current kernel to CombinedKernel
# combined_kernel.append_kernel(kernel)
#
# # append features
# combined_features.append_feature_obj(base_features)
#
# print "------"
#
# ##################################################
# # all blocks
#
#
# all_block_vec = PairiiVec()
#
# for task_id_1 in data.get_task_ids():
# for task_id_2 in data.get_task_ids():
# all_block_vec.push_back(Pairii(task_id_1, task_id_2))
#
#
# # create mask-based normalizer
# normalizer_all = MultitaskKernelMaskPairNormalizer(data.task_vector_nums, all_block_vec)
# kernel_all = shogun_factory.create_empty_kernel(param)
# kernel_all.set_normalizer(normalizer_all)
#
# # append current kernel to CombinedKernel
# combined_kernel.append_kernel(kernel_all)
#
# # append features
# combined_features.append_feature_obj(base_features)
##################################################
# add one kernel per similarity position
# init seq handler
pseudoseqs = SequencesHandler()
for pocket in pockets:
print "creating normalizer"
#import pdb
#pdb.set_trace()
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
print "processing pocket", pocket
# set similarity
for task_name_lhs in data.get_task_names():
for task_name_rhs in data.get_task_names():
similarity = 0.0
for pseudo_seq_pos in pocket:
similarity += float(
pseudoseqs.get_similarity(task_name_lhs,
task_name_rhs,
pseudo_seq_pos - 1))
# normalize
similarity = similarity / float(len(pocket))
print "pocket %s (%s, %s) = %f" % (
str(pocket), task_name_lhs, task_name_rhs, similarity)
normalizer.set_task_similarity(
data.name_to_id(task_name_lhs),
data.name_to_id(task_name_rhs), similarity)
print "creating empty kernel"
kernel_pos = shogun_factory.create_empty_kernel(param)
print "setting normalizer"
kernel_pos.set_normalizer(normalizer)
print "appending kernel"
# append current kernel to CombinedKernel
combined_kernel.append_kernel(kernel_pos)
print "appending features"
# append features
combined_features.append_feature_obj(base_features)
print "done constructing combined kernel"
##################################################
# init combined kernel
# init weights
# combined_kernel.set_subkernel_weights([1.0/2.85]*combined_kernel.get_num_subkernels())
combined_kernel.init(combined_features, combined_features)
print "subkernel weights:", combined_kernel.get_subkernel_weights()
svm = None
print "using MKL:", (param.transform >= 1.0)
if param.transform >= 1.0:
svm = MKLClassification()
svm.set_mkl_norm(param.transform)
#svm.set_solver_type(ST_CPLEX) #ST_GLPK) #DIRECT) #NEWTON)#ST_CPLEX) #auto
svm.set_C(param.cost, param.cost)
svm.set_kernel(combined_kernel)
svm.set_labels(lab)
else:
# create SVM (disable unsupported optimizations)
combined_kernel.set_cache_size(500)
svm = SVMLight(param.cost, combined_kernel, lab)
# set up SVM
num_threads = 8
svm.io.enable_progress()
#svm.io.set_loglevel(shogun.Classifier.MSG_INFO)
svm.io.set_loglevel(shogun.Classifier.MSG_DEBUG)
svm.parallel.set_num_threads(num_threads)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
#print "WARNING: custom epsilon set"
#svm.set_epsilon(0.05)
# normalize cost
norm_c_pos = param.cost / float(len([l
for l in data.labels if l == 1]))
norm_c_neg = param.cost / float(
len([l for l in data.labels if l == -1]))
svm.set_C(norm_c_neg, norm_c_pos)
# start training
svm.train()
# save additional info
self.additional_information["svm_objective"] = svm.get_objective()
self.additional_information[
"svm num sv"] = svm.get_num_support_vectors()
self.additional_information[
"post_weights"] = combined_kernel.get_subkernel_weights()
print self.additional_information
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in train_data.keys():
svms[task_name] = (data.name_to_id(task_name), combined_kernel,
svm)
return svms
N = subset_size
##################################################################
# internal modification
##################################################################
task_vector = [0]*(N/2)
task_vector.extend([1]*(N/2))
base_wdk = WeightedDegreeStringKernel(feat, feat, 1)
normalizer = MultitaskKernelNormalizer(task_vector)
#wdk.set_task_vector(task_vector) #, task_vector)
for i in xrange(2):
for j in xrange(2):
if i==j:
normalizer.set_task_similarity(i,j, 4.0)
else:
normalizer.set_task_similarity(i,j, 1.0)
base_wdk.set_normalizer(normalizer)
print base_wdk.get_kernel_matrix()
def test_data():
##################################################################
# select MSS
##################################################################
mss = expenv.MultiSplitSet.get(379)
##################################################################
# data
##################################################################
# fetch data
instance_set = mss.get_train_data(-1)
# prepare data
data = PreparedMultitaskData(instance_set, shuffle=True)
# set parameters
param = Options()
param.kernel = "WeightedDegreeStringKernel"
param.wdk_degree = 4
param.cost = 1.0
param.transform = 1.0
param.id = 666
param.freeze()
##################################################################
# taxonomy
##################################################################
taxonomy = shogun_factory.create_taxonomy(mss.taxonomy.data)
support = numpy.linspace(0, 100, 4)
distances = [[0, 1, 2, 2], [1, 0, 2, 2], [2, 2, 0, 1], [2, 2, 1, 0]]
# create tree normalizer
tree_normalizer = MultitaskKernelPlifNormalizer(support, data.task_vector_names)
task_names = data.get_task_names()
FACTOR = 1.0
# init gamma matrix
gammas = numpy.zeros((data.get_num_tasks(), data.get_num_tasks()))
for t1_name in task_names:
for t2_name in task_names:
similarity = taxonomy.compute_node_similarity(taxonomy.get_id(t1_name), taxonomy.get_id(t2_name))
gammas[data.name_to_id(t1_name), data.name_to_id(t2_name)] = similarity
helper.save("/tmp/gammas", gammas)
gammas = gammas * FACTOR
cost = param.cost * numpy.sqrt(FACTOR)
print gammas
##########
# regular normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
for t1_name in task_names:
for t2_name in task_names:
similarity = gammas[data.name_to_id(t1_name), data.name_to_id(t2_name)]
normalizer.set_task_similarity(data.name_to_id(t1_name), data.name_to_id(t2_name), similarity)
##################################################################
# Train SVMs
##################################################################
# create shogun objects
wdk_tree = shogun_factory.create_kernel(data.examples, param)
lab = shogun_factory.create_labels(data.labels)
wdk_tree.set_normalizer(tree_normalizer)
wdk_tree.init_normalizer()
print "--->",wdk_tree.get_normalizer().get_name()
svm_tree = SVMLight(cost, wdk_tree, lab)
svm_tree.set_linadd_enabled(False)
svm_tree.set_batch_computation_enabled(False)
svm_tree.train()
del wdk_tree
del tree_normalizer
print "finished training tree-norm SVM:", svm_tree.get_objective()
wdk = shogun_factory.create_kernel(data.examples, param)
wdk.set_normalizer(normalizer)
wdk.init_normalizer()
print "--->",wdk.get_normalizer().get_name()
svm = SVMLight(cost, wdk, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
svm.train()
print "finished training manually set SVM:", svm.get_objective()
alphas_tree = svm_tree.get_alphas()
alphas = svm.get_alphas()
assert(len(alphas_tree)==len(alphas))
for i in xrange(len(alphas)):
assert(abs(alphas_tree[i] - alphas[i]) < 0.0001)
print "success: all alphas are the same"
def solver_mtk_shogun(C, all_xt, all_lt, task_indicator, M, L, eps,
target_obj):
"""
implementation using multitask kernel
"""
xt = numpy.array(all_xt)
lt = numpy.array(all_lt)
tt = numpy.array(task_indicator, dtype=numpy.int32)
tsm = numpy.array(M)
print "task_sim:", tsm
num_tasks = L.shape[0]
# sanity checks
assert len(xt) == len(lt) == len(tt)
assert M.shape == L.shape
assert num_tasks == len(set(tt))
# set up shogun objects
if type(xt[0]) == numpy.string_:
feat = StringCharFeatures(DNA)
xt = [str(a) for a in xt]
feat.set_features(xt)
base_kernel = WeightedDegreeStringKernel(feat, feat, 8)
else:
feat = RealFeatures(xt.T)
base_kernel = LinearKernel(feat, feat)
lab = Labels(lt)
# set up normalizer
normalizer = MultitaskKernelNormalizer(tt.tolist())
for i in xrange(num_tasks):
for j in xrange(num_tasks):
normalizer.set_task_similarity(i, j, M[i, j])
print "num of unique tasks: ", normalizer.get_num_unique_tasks(
task_indicator)
# set up kernel
base_kernel.set_cache_size(2000)
base_kernel.set_normalizer(normalizer)
base_kernel.init_normalizer()
# set up svm
svm = SVMLight() #LibSVM()
svm.set_epsilon(eps)
#print "reducing num threads to one"
#svm.parallel.set_num_threads(1)
#print "using one thread"
# how often do we like to compute objective etc
svm.set_record_interval(0)
svm.set_target_objective(target_obj)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
svm.io.set_loglevel(MSG_DEBUG)
#SET THREADS TO 1
svm.set_C(C, C)
svm.set_bias_enabled(False)
# prepare for training
svm.set_labels(lab)
svm.set_kernel(base_kernel)
# train svm
svm.train()
train_times = svm.get_training_times()
objectives = [-obj for obj in svm.get_dual_objectives()]
if False:
# get model parameters
sv_idx = svm.get_support_vectors()
sparse_alphas = svm.get_alphas()
assert len(sv_idx) == len(sparse_alphas)
# compute dense alpha (remove label)
alphas = numpy.zeros(len(xt))
for id_sparse, id_dense in enumerate(sv_idx):
alphas[id_dense] = sparse_alphas[id_sparse] * lt[id_dense]
# print alphas
W = alphas_to_w(alphas, xt, lt, task_indicator, M)
primal_obj = compute_primal_objective(
W.reshape(W.shape[0] * W.shape[1]), C, all_xt, all_lt,
task_indicator, L)
objectives.append(primal_obj)
train_times.append(train_times[-1] + 100)
return objectives, train_times
def test_data():
##################################################################
# select MSS
##################################################################
mss = expenv.MultiSplitSet.get(379)
##################################################################
# data
##################################################################
# fetch data
instance_set = mss.get_train_data(-1)
# prepare data
data = PreparedMultitaskData(instance_set, shuffle=True)
# set parameters
param = Options()
param.kernel = "WeightedDegreeStringKernel"
param.wdk_degree = 4
param.cost = 1.0
param.transform = 1.0
param.id = 666
param.freeze()
##################################################################
# taxonomy
##################################################################
taxonomy = shogun_factory.create_taxonomy(mss.taxonomy.data)
support = numpy.linspace(0, 100, 4)
distances = [[0, 1, 2, 2], [1, 0, 2, 2], [2, 2, 0, 1], [2, 2, 1, 0]]
# create tree normalizer
tree_normalizer = MultitaskKernelPlifNormalizer(support,
data.task_vector_names)
task_names = data.get_task_names()
FACTOR = 1.0
# init gamma matrix
gammas = numpy.zeros((data.get_num_tasks(), data.get_num_tasks()))
for t1_name in task_names:
for t2_name in task_names:
similarity = taxonomy.compute_node_similarity(
taxonomy.get_id(t1_name), taxonomy.get_id(t2_name))
gammas[data.name_to_id(t1_name),
data.name_to_id(t2_name)] = similarity
helper.save("/tmp/gammas", gammas)
gammas = gammas * FACTOR
cost = param.cost * numpy.sqrt(FACTOR)
print gammas
##########
# regular normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
for t1_name in task_names:
for t2_name in task_names:
similarity = gammas[data.name_to_id(t1_name),
data.name_to_id(t2_name)]
normalizer.set_task_similarity(data.name_to_id(t1_name),
data.name_to_id(t2_name),
similarity)
##################################################################
# Train SVMs
##################################################################
# create shogun objects
wdk_tree = shogun_factory.create_kernel(data.examples, param)
lab = shogun_factory.create_labels(data.labels)
wdk_tree.set_normalizer(tree_normalizer)
wdk_tree.init_normalizer()
print "--->", wdk_tree.get_normalizer().get_name()
svm_tree = SVMLight(cost, wdk_tree, lab)
svm_tree.set_linadd_enabled(False)
svm_tree.set_batch_computation_enabled(False)
svm_tree.train()
del wdk_tree
del tree_normalizer
print "finished training tree-norm SVM:", svm_tree.get_objective()
wdk = shogun_factory.create_kernel(data.examples, param)
wdk.set_normalizer(normalizer)
wdk.init_normalizer()
print "--->", wdk.get_normalizer().get_name()
svm = SVMLight(cost, wdk, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
svm.train()
print "finished training manually set SVM:", svm.get_objective()
alphas_tree = svm_tree.get_alphas()
alphas = svm.get_alphas()
assert (len(alphas_tree) == len(alphas))
for i in xrange(len(alphas)):
assert (abs(alphas_tree[i] - alphas[i]) < 0.0001)
print "success: all alphas are the same"
similarity = taxonomy.compute_node_similarity(taxonomy.get_id(t1_name),
taxonomy.get_id(t2_name))
gammas[data.name_to_id(t1_name), data.name_to_id(t2_name)] = similarity
helper.save("/tmp/gammas", gammas)
gammas = gammas * FACTOR
cost = param.cost * numpy.sqrt(FACTOR)
print gammas
##########
# regular normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
for t1_name in task_names:
for t2_name in task_names:
similarity = gammas[data.name_to_id(t1_name), data.name_to_id(t2_name)]
normalizer.set_task_similarity(data.name_to_id(t1_name),
data.name_to_id(t2_name), similarity)
##################################################################
# Train SVMs
##################################################################
# create shogun objects
wdk_tree = shogun_factory.create_kernel(data.examples, param)
lab = shogun_factory.create_labels(data.labels)
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
# merge data sets
data = PreparedMultitaskData(train_data, shuffle=False)
# create shogun data objects
base_wdk = shogun_factory.create_empty_kernel(param)
lab = shogun_factory.create_labels(data.labels)
combined_kernel = CombinedKernel()
combined_kernel.io.set_loglevel(shogun.Kernel.MSG_INFO)
base_features = shogun_factory.create_features(data.examples)
combined_features = CombinedFeatures()
# set normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
# load data
#f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/ALL_PseudoSeq_BlosumEnc_pearson.txt")
f = file(
"/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/All_PseudoSeq_Hamming.txt"
)
#f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/ALL_PseudoSeq_BlosumEnc_euklid.txt")
#f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/ALL_RAxML.txt")
num_lines = int(f.readline().strip())
task_distances = numpy.zeros((num_lines, num_lines))
name_to_id = {}
for (i, line) in enumerate(f):
tokens = line.strip().split("\t")
name = str(tokens[0])
name_to_id[name] = i
entry = numpy.array([v for (j, v) in enumerate(tokens) if j != 0])
assert len(entry) == num_lines, "len_entry %i, num_lines %i" % (
len(entry), num_lines)
task_distances[i, :] = entry
# cut relevant submatrix
active_ids = [name_to_id[name] for name in data.get_task_names()]
tmp_distances = task_distances[active_ids, :]
tmp_distances = tmp_distances[:, active_ids]
print "distances ", tmp_distances.shape
# normalize distances
task_distances = task_distances / numpy.max(tmp_distances)
similarities = numpy.zeros(
(data.get_num_tasks(), data.get_num_tasks()))
# convert distance to similarity
for task_name_lhs in data.get_task_names():
for task_name_rhs in data.get_task_names():
# convert similarity with simple transformation
similarity = param.base_similarity - task_distances[
name_to_id[task_name_lhs], name_to_id[task_name_rhs]]
normalizer.set_task_similarity(data.name_to_id(task_name_lhs),
data.name_to_id(task_name_rhs),
similarity)
# save for later
similarities[data.name_to_id(task_name_lhs),
data.name_to_id(task_name_rhs)] = similarity
# set normalizer
base_wdk.set_normalizer(normalizer)
#base_wdk.init_normalizer()
combined_features.append_feature_obj(base_features)
combined_kernel.append_kernel(base_wdk)
##################################################
# intra-domain blocks
intra_block_vec = PairiiVec()
for task_id in data.get_task_ids():
intra_block_vec.push_back(Pairii(task_id, task_id))
# create mask-based normalizer
normalizer = MultitaskKernelMaskPairNormalizer(data.task_vector_nums,
intra_block_vec)
kernel = shogun_factory.create_empty_kernel(param)
kernel.set_normalizer(normalizer)
# append current kernel to CombinedKernel
combined_kernel.append_kernel(kernel)
# append features
combined_features.append_feature_obj(base_features)
# set mixing factor (used if MKL is OFF)
assert (param.base_similarity <= 1)
assert (param.base_similarity >= 0)
combined_kernel.set_subkernel_weights(
[param.base_similarity, 1 - param.base_similarity])
combined_kernel.init(combined_features, combined_features)
svm = None
print "using MKL:", (param.transform >= 1.0)
if param.transform >= 1.0:
svm = MKLClassification()
svm.set_mkl_norm(param.transform)
#svm.set_solver_type(ST_CPLEX) #ST_GLPK) #DIRECT) #NEWTON)#ST_CPLEX) #auto
svm.set_C(param.cost, param.cost)
svm.set_kernel(combined_kernel)
svm.set_labels(lab)
else:
# create SVM (disable unsupported optimizations)
combined_kernel.set_cache_size(500)
svm = SVMLight(param.cost, combined_kernel, lab)
# set up SVM
num_threads = 8
svm.io.enable_progress()
svm.io.set_loglevel(shogun.Classifier.MSG_DEBUG)
svm.parallel.set_num_threads(num_threads)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
print "WARNING: custom epsilon set"
svm.set_epsilon(0.05)
# normalize cost
norm_c_pos = param.cost / float(len([l
for l in data.labels if l == 1]))
norm_c_neg = param.cost / float(
len([l for l in data.labels if l == -1]))
svm.set_C(norm_c_neg, norm_c_pos)
# start training
svm.train()
# save additional information
self.additional_information["svm objective"] = svm.get_objective()
self.additional_information["num sv"] = svm.get_num_support_vectors()
self.additional_information["similarities"] = similarities
self.additional_information[
"post_weights"] = combined_kernel.get_subkernel_weights()
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in data.get_task_names():
task_num = data.name_to_id(task_name)
# save svm and task_num
svms[task_name] = (task_num, combined_kernel, svm)
return svms
def _inner_train(self, prepared_data, param):
"""
perform inner training by processing the tree
"""
# init seq handler
classifiers = []
#################
# mtk
normalizer = MultitaskKernelNormalizer(prepared_data.task_vector_nums)
from method_mhc_rbf import SequencesHandlerRbf
task_kernel = SequencesHandlerRbf(1, param.base_similarity,
prepared_data.get_task_names(),
param.flags["wdk_rbf_on"])
# set similarity
for task_name_lhs in prepared_data.get_task_names():
for task_name_rhs in prepared_data.get_task_names():
similarity = task_kernel.get_similarity(
task_name_lhs, task_name_rhs)
normalizer.set_task_similarity(
prepared_data.name_to_id(task_name_lhs),
prepared_data.name_to_id(task_name_rhs), similarity)
lab = shogun_factory.create_labels(prepared_data.labels)
print "creating empty kernel"
kernel = shogun_factory.create_kernel(prepared_data.examples, param)
print "setting normalizer"
kernel.set_normalizer(normalizer)
kernel.init_normalizer()
svm = shogun_factory.create_svm(param, kernel, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
# train SVM
svm.train()
classifiers.append(svm)
#################
# dirac
#import pdb
#pdb.set_trace()
svm_dirac = self._dirac_train(prepared_data, param)
classifiers.append(svm_dirac)
##
#union
#svm_union = self._union_train(prepared_data, param)
#classifiers.append(svm_union)
return classifiers
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
assert(param.base_similarity >= 1)
# merge data sets
data = PreparedMultitaskData(train_data, shuffle=False)
# create shogun data objects
base_wdk = shogun_factory.create_kernel(data.examples, param)
lab = shogun_factory.create_labels(data.labels)
# create normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
# load hard-coded task-similarity
task_similarity = helper.load("/fml/ag-raetsch/home/cwidmer/svn/projects/alt_splice_code/src/task_sim_tis.bz2")
# set similarity
similarities = numpy.zeros((data.get_num_tasks(), data.get_num_tasks()))
for (i, task_name_lhs) in enumerate(data.get_task_names()):
#max_value_row = max(task_similarity.get_row(task_name_lhs))
max_value_row = 1.0
for (j, task_name_rhs) in enumerate(data.get_task_names()):
similarity = task_similarity.get_value(task_name_lhs, task_name_rhs) / max_value_row
normalizer.set_task_similarity(i, j, similarity)
similarities[i,j] = similarity
pprint.pprint similarities
# set normalizer
#print "WARNING MTK disabled!!!!!!!!!!!!!!!!!!!!!"
base_wdk.set_normalizer(normalizer)
base_wdk.init_normalizer()
# set up svm
param.flags["svm_type"] = "svmlight" #fix svm type
svm = shogun_factory.create_svm(param, base_wdk, lab)
# make sure these parameters are set correctly
#print "WARNING MTK WONT WORK WITH THESE SETTINGS!!!!!!!!!!!!!!!!!!!!!"
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
assert svm.get_linadd_enabled() == False, "linadd should be disabled"
assert svm.get_batch_computation_enabled == False, "batch compute should be disabled"
# start training
svm.train()
# save additional information
self.additional_information["svm objective"] = svm.get_objective()
self.additional_information["num sv"] = svm.get_num_support_vectors()
#self.additional_information["distances"] = distances
self.additional_information["similarities"] = similarities
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in data.get_task_names():
task_num = data.name_to_id(task_name)
# save svm and task_num
svms[task_name] = (task_num, svm)
return svms
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
# split for training weak_learners and boosting
(train_weak, train_boosting) = split_data(train_data, 4)
# merge data sets
data = PreparedMultitaskData(train_weak, shuffle=True)
# create shogun label
lab = shogun_factory.create_labels(data.labels)
##################################################
# define pockets
##################################################
pockets = [0]*9
pockets[0] = [1, 5, 6, 7, 8, 31, 32, 33, 34]
pockets[1] = [1, 2, 3, 4, 6, 7, 8, 9, 11, 21, 31]
pockets[2] = [11, 20, 21, 22, 29, 31]
pockets[3] = [8, 30, 31, 32]
pockets[4] = [10, 11, 30]
pockets[5] = [10, 11, 12, 13, 20, 29]
pockets[6] = [10, 12, 20, 22, 26, 27, 28, 29]
pockets[7] = [12, 14, 15, 26]
pockets[8] = [13, 15, 16, 17, 18, 19, 20, 23, 24, 25, 26]
pockets = []
for i in xrange(35):
pockets.append([i])
#new_pockets = []
# merge neighboring pockets
#for i in range(8):
# new_pockets.append(list(set(pockets[i]).union(set(pockets[i+1]))))
#pockets = new_pockets
########################################################
print "creating a kernel:"
########################################################
# init seq handler
pseudoseqs = SequencesHandler()
classifiers = []
for pocket in pockets:
print "creating normalizer"
#import pdb
#pdb.set_trace()
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
print "processing pocket", pocket
# set similarity
for task_name_lhs in data.get_task_names():
for task_name_rhs in data.get_task_names():
similarity = 0.0
for pseudo_seq_pos in pocket:
similarity += float(pseudoseqs.get_similarity(task_name_lhs, task_name_rhs, pseudo_seq_pos-1))
# normalize
similarity = similarity / float(len(pocket))
print "pocket %s (%s, %s) = %f" % (str(pocket), task_name_lhs, task_name_rhs, similarity)
normalizer.set_task_similarity(data.name_to_id(task_name_lhs), data.name_to_id(task_name_rhs), similarity)
print "creating empty kernel"
kernel = shogun_factory.create_kernel(data.examples, param)
print "setting normalizer"
kernel.set_normalizer(normalizer)
print "training SVM for pocket", pocket
svm = self._train_single_svm(param, kernel, lab)
classifiers.append(svm)
print "done obtaining weak learners"
# save additional info
#self.additional_information["svm_objective"] = svm.get_objective()
#self.additional_information["svm num sv"] = svm.get_num_support_vectors()
#self.additional_information["post_weights"] = combined_kernel.get_subkernel_weights()
#print self.additional_information
##################################################
# combine weak learners for each task
##################################################
# set constants
some = 0.9
import cvxmod
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in train_boosting.keys():
instances = train_boosting[task_name]
N = len(instances)
F = len(pockets)
examples = [inst.example for inst in instances]
labels = [inst.label for inst in instances]
# dim = (F x N)
out = cvxmod.zeros((N,F))
for i in xrange(F):
svm = classifiers[i]
tmp_out = self._predict_weak(svm, examples, data.name_to_id(task_name))
out[:,i] = numpy.sign(tmp_out)
#out[:,i] = tmp_out
#TODO: fix
helper.save("/tmp/out_sparse", (out,labels))
pdb.set_trace()
weights = solve_boosting(out, labels, some, solver="mosek")
svms[task_name] = (data.name_to_id(task_name), svm)
return svms
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
# merge data sets
data = PreparedMultitaskData(train_data, shuffle=False)
# create shogun data objects
base_wdk = shogun_factory.create_kernel(data.examples, param)
lab = shogun_factory.create_labels(data.labels)
# set normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
########################################################
print "creating a kernel for each node:"
########################################################
# init seq handler
task_kernel = SequencesHandlerRbf(1, param.base_similarity, data.get_task_names(), param.flags["wdk_rbf_on"])
similarities = numpy.zeros((data.get_num_tasks(), data.get_num_tasks()))
# convert distance to similarity
for task_name_lhs in data.get_task_names():
for task_name_rhs in data.get_task_names():
# convert similarity with simple transformation
similarity = task_kernel.get_similarity(task_name_lhs, task_name_rhs)
print similarity
print "similarity (%s,%s)=%f" % (task_name_lhs, task_name_rhs, similarity)
normalizer.set_task_similarity(data.name_to_id(task_name_lhs), data.name_to_id(task_name_rhs), similarity)
# save for later
similarities[data.name_to_id(task_name_lhs),data.name_to_id(task_name_rhs)] = similarity
# set normalizer
base_wdk.set_normalizer(normalizer)
base_wdk.init_normalizer()
# set up svm
svm = SVMLight(param.cost, base_wdk, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
# normalize cost
norm_c_pos = param.cost / float(len([l for l in data.labels if l==1]))
norm_c_neg = param.cost / float(len([l for l in data.labels if l==-1]))
svm.set_C(norm_c_neg, norm_c_pos)
# start training
svm.train()
# save additional information
self.additional_information["svm objective"] = svm.get_objective()
self.additional_information["num sv"] = svm.get_num_support_vectors()
#self.additional_information["distances"] = distances
self.additional_information["similarities"] = similarities
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in data.get_task_names():
task_num = data.name_to_id(task_name)
# save svm and task_num
svms[task_name] = (task_num, param, svm)
return svms
feat = StringCharFeatures(DNA)
feat.set_features(examples)
lab = Labels(numpy.array(labels))
N = subset_size
##################################################################
# internal modification
##################################################################
task_vector = [0] * (N / 2)
task_vector.extend([1] * (N / 2))
base_wdk = WeightedDegreeStringKernel(feat, feat, 1)
normalizer = MultitaskKernelNormalizer(task_vector)
#wdk.set_task_vector(task_vector) #, task_vector)
for i in xrange(2):
for j in xrange(2):
if i == j:
normalizer.set_task_similarity(i, j, 4.0)
else:
normalizer.set_task_similarity(i, j, 1.0)
base_wdk.set_normalizer(normalizer)
print base_wdk.get_kernel_matrix()
print "--->", base_wdk.get_normalizer().get_name()
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
# merge data sets
data = PreparedMultitaskData(train_data, shuffle=True)
# create shogun label
lab = shogun_factory.create_labels(data.labels)
##################################################
# define pockets
##################################################
pockets = [0]*9
pockets[0] = [1, 5, 6, 7, 8, 31, 32, 33, 34]
pockets[1] = [1, 2, 3, 4, 6, 7, 8, 9, 11, 21, 31]
pockets[2] = [11, 20, 21, 22, 29, 31]
pockets[3] = [8, 30, 31, 32]
pockets[4] = [10, 11, 30]
pockets[5] = [10, 11, 12, 13, 20, 29]
pockets[6] = [10, 12, 20, 22, 26, 27, 28, 29]
pockets[7] = [12, 14, 15, 26]
pockets[8] = [13, 15, 16, 17, 18, 19, 20, 23, 24, 25, 26]
#new_pockets = []
# merge neighboring pockets
#for i in range(8):
# new_pockets.append(list(set(pockets[i]).union(set(pockets[i+1]))))
#pockets = new_pockets
########################################################
print "creating a kernel:"
########################################################
# assemble combined kernel
combined_kernel = CombinedKernel()
combined_kernel.io.set_loglevel(shogun.Kernel.MSG_INFO)
base_features = shogun_factory.create_features(data.examples)
combined_features = CombinedFeatures()
##################################################
# intra-domain blocks
# intra_block_vec = PairiiVec()
#
# for task_id in data.get_task_ids():
# intra_block_vec.push_back(Pairii(task_id, task_id))
#
#
#
# # create mask-based normalizer
# normalizer = MultitaskKernelMaskPairNormalizer(data.task_vector_nums, intra_block_vec)
# kernel = shogun_factory.create_empty_kernel(param)
# kernel.set_normalizer(normalizer)
#
# # append current kernel to CombinedKernel
# combined_kernel.append_kernel(kernel)
#
# # append features
# combined_features.append_feature_obj(base_features)
#
# print "------"
#
# ##################################################
# # all blocks
#
#
# all_block_vec = PairiiVec()
#
# for task_id_1 in data.get_task_ids():
# for task_id_2 in data.get_task_ids():
# all_block_vec.push_back(Pairii(task_id_1, task_id_2))
#
#
# # create mask-based normalizer
# normalizer_all = MultitaskKernelMaskPairNormalizer(data.task_vector_nums, all_block_vec)
# kernel_all = shogun_factory.create_empty_kernel(param)
# kernel_all.set_normalizer(normalizer_all)
#
# # append current kernel to CombinedKernel
# combined_kernel.append_kernel(kernel_all)
#
# # append features
# combined_features.append_feature_obj(base_features)
##################################################
# add one kernel per similarity position
# init seq handler
pseudoseqs = SequencesHandler()
for pocket in pockets:
print "creating normalizer"
#import pdb
#pdb.set_trace()
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
print "processing pocket", pocket
# set similarity
for task_name_lhs in data.get_task_names():
for task_name_rhs in data.get_task_names():
similarity = 0.0
for pseudo_seq_pos in pocket:
similarity += float(pseudoseqs.get_similarity(task_name_lhs, task_name_rhs, pseudo_seq_pos-1))
# normalize
similarity = similarity / float(len(pocket))
print "pocket %s (%s, %s) = %f" % (str(pocket), task_name_lhs, task_name_rhs, similarity)
normalizer.set_task_similarity(data.name_to_id(task_name_lhs), data.name_to_id(task_name_rhs), similarity)
print "creating empty kernel"
kernel_pos = shogun_factory.create_empty_kernel(param)
print "setting normalizer"
kernel_pos.set_normalizer(normalizer)
print "appending kernel"
# append current kernel to CombinedKernel
combined_kernel.append_kernel(kernel_pos)
print "appending features"
# append features
combined_features.append_feature_obj(base_features)
print "done constructing combined kernel"
##################################################
# init combined kernel
# init weights
# combined_kernel.set_subkernel_weights([1.0/2.85]*combined_kernel.get_num_subkernels())
combined_kernel.init(combined_features, combined_features)
print "subkernel weights:", combined_kernel.get_subkernel_weights()
svm = None
print "using MKL:", (param.transform >= 1.0)
if param.transform >= 1.0:
svm = MKLClassification()
svm.set_mkl_norm(param.transform)
#svm.set_solver_type(ST_CPLEX) #ST_GLPK) #DIRECT) #NEWTON)#ST_CPLEX) #auto
svm.set_C(param.cost, param.cost)
svm.set_kernel(combined_kernel)
svm.set_labels(lab)
else:
# create SVM (disable unsupported optimizations)
combined_kernel.set_cache_size(500)
svm = SVMLight(param.cost, combined_kernel, lab)
# set up SVM
num_threads = 8
svm.io.enable_progress()
#svm.io.set_loglevel(shogun.Classifier.MSG_INFO)
svm.io.set_loglevel(shogun.Classifier.MSG_DEBUG)
svm.parallel.set_num_threads(num_threads)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
#print "WARNING: custom epsilon set"
#svm.set_epsilon(0.05)
# normalize cost
norm_c_pos = param.cost / float(len([l for l in data.labels if l==1]))
norm_c_neg = param.cost / float(len([l for l in data.labels if l==-1]))
svm.set_C(norm_c_neg, norm_c_pos)
# start training
svm.train()
# save additional info
self.additional_information["svm_objective"] = svm.get_objective()
self.additional_information["svm num sv"] = svm.get_num_support_vectors()
self.additional_information["post_weights"] = combined_kernel.get_subkernel_weights()
print self.additional_information
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in train_data.keys():
svms[task_name] = (data.name_to_id(task_name), combined_kernel, svm)
return svms
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
assert(param.base_similarity >= 1)
# merge data sets
data = PreparedMultitaskData(train_data, shuffle=False)
# create shogun data objects
base_wdk = shogun_factory.create_kernel(data.examples, param)
lab = shogun_factory.create_labels(data.labels)
# set normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
# load data
#f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/ALL_PseudoSeq_BlosumEnc_pearson.txt")
f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/All_PseudoSeq_Hamming.txt")
#f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/ALL_PseudoSeq_BlosumEnc_euklid.txt")
#f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/ALL_RAxML.txt")
num_lines = int(f.readline().strip())
task_distances = numpy.zeros((num_lines, num_lines))
name_to_id = {}
for (i, line) in enumerate(f):
tokens = line.strip().split("\t")
name = str(tokens[0])
name_to_id[name] = i
entry = numpy.array([v for (j,v) in enumerate(tokens) if j!=0])
assert len(entry)==num_lines, "len_entry %i, num_lines %i" % (len(entry), num_lines)
task_distances[i,:] = entry
# cut relevant submatrix
active_ids = [name_to_id[name] for name in data.get_task_names()]
tmp_distances = task_distances[active_ids, :]
tmp_distances = tmp_distances[:, active_ids]
print "distances ", tmp_distances.shape
# normalize distances
task_distances = task_distances / numpy.max(tmp_distances)
similarities = numpy.zeros((data.get_num_tasks(), data.get_num_tasks()))
# convert distance to similarity
for task_name_lhs in data.get_task_names():
for task_name_rhs in data.get_task_names():
# convert similarity with simple transformation
similarity = param.base_similarity - task_distances[name_to_id[task_name_lhs], name_to_id[task_name_rhs]]
normalizer.set_task_similarity(data.name_to_id(task_name_lhs), data.name_to_id(task_name_rhs), similarity)
# save for later
similarities[data.name_to_id(task_name_lhs),data.name_to_id(task_name_rhs)] = similarity
# set normalizer
base_wdk.set_normalizer(normalizer)
base_wdk.init_normalizer()
# set up svm
svm = SVMLight(param.cost, base_wdk, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
# normalize cost
norm_c_pos = param.cost / float(len([l for l in data.labels if l==1]))
norm_c_neg = param.cost / float(len([l for l in data.labels if l==-1]))
svm.set_C(norm_c_neg, norm_c_pos)
# start training
svm.train()
# save additional information
self.additional_information["svm objective"] = svm.get_objective()
self.additional_information["num sv"] = svm.get_num_support_vectors()
#self.additional_information["distances"] = distances
self.additional_information["similarities"] = similarities
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in data.get_task_names():
task_num = data.name_to_id(task_name)
# save svm and task_num
svms[task_name] = (task_num, param, svm)
return svms
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
assert (param.base_similarity >= 1)
# merge data sets
data = PreparedMultitaskData(train_data, shuffle=False)
# create shogun data objects
base_wdk = shogun_factory.create_kernel(data.examples, param)
lab = shogun_factory.create_labels(data.labels)
# set normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
# load data
#f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/ALL_PseudoSeq_BlosumEnc_pearson.txt")
f = file(
"/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/All_PseudoSeq_Hamming.txt"
)
#f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/ALL_PseudoSeq_BlosumEnc_euklid.txt")
#f = file("/fml/ag-raetsch/home/cwidmer/Documents/phd/projects/multitask/data/mhc/MHC_Distanzen/MHC_Distanzen/ALL_RAxML.txt")
num_lines = int(f.readline().strip())
task_distances = numpy.zeros((num_lines, num_lines))
name_to_id = {}
for (i, line) in enumerate(f):
tokens = line.strip().split("\t")
name = str(tokens[0])
name_to_id[name] = i
entry = numpy.array([v for (j, v) in enumerate(tokens) if j != 0])
assert len(entry) == num_lines, "len_entry %i, num_lines %i" % (
len(entry), num_lines)
task_distances[i, :] = entry
# cut relevant submatrix
active_ids = [name_to_id[name] for name in data.get_task_names()]
tmp_distances = task_distances[active_ids, :]
tmp_distances = tmp_distances[:, active_ids]
print "distances ", tmp_distances.shape
# normalize distances
task_distances = task_distances / numpy.max(tmp_distances)
similarities = numpy.zeros(
(data.get_num_tasks(), data.get_num_tasks()))
# convert distance to similarity
for task_name_lhs in data.get_task_names():
for task_name_rhs in data.get_task_names():
# convert similarity with simple transformation
similarity = param.base_similarity - task_distances[
name_to_id[task_name_lhs], name_to_id[task_name_rhs]]
normalizer.set_task_similarity(data.name_to_id(task_name_lhs),
data.name_to_id(task_name_rhs),
similarity)
# save for later
similarities[data.name_to_id(task_name_lhs),
data.name_to_id(task_name_rhs)] = similarity
# set normalizer
base_wdk.set_normalizer(normalizer)
base_wdk.init_normalizer()
# set up svm
svm = SVMLight(param.cost, base_wdk, lab)
svm.set_linadd_enabled(False)
svm.set_batch_computation_enabled(False)
# normalize cost
norm_c_pos = param.cost / float(len([l
for l in data.labels if l == 1]))
norm_c_neg = param.cost / float(
len([l for l in data.labels if l == -1]))
svm.set_C(norm_c_neg, norm_c_pos)
# start training
svm.train()
# save additional information
self.additional_information["svm objective"] = svm.get_objective()
self.additional_information["num sv"] = svm.get_num_support_vectors()
#self.additional_information["distances"] = distances
self.additional_information["similarities"] = similarities
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in data.get_task_names():
task_num = data.name_to_id(task_name)
# save svm and task_num
svms[task_name] = (task_num, param, svm)
return svms
gammas[data.name_to_id(t1_name), data.name_to_id(t2_name)] = similarity
helper.save("/tmp/gammas", gammas)
gammas = gammas * FACTOR
cost = param.cost * numpy.sqrt(FACTOR)
print gammas
##########
# regular normalizer
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
for t1_name in task_names:
for t2_name in task_names:
similarity = gammas[data.name_to_id(t1_name), data.name_to_id(t2_name)]
normalizer.set_task_similarity(data.name_to_id(t1_name), data.name_to_id(t2_name), similarity)
##################################################################
# Train SVMs
##################################################################
# create shogun objects
wdk_tree = shogun_factory.create_kernel(data.examples, param)
lab = shogun_factory.create_labels(data.labels)
def _train(self, train_data, param):
"""
training procedure using training examples and labels
@param train_data: Data relevant to SVM training
@type train_data: dict<str, list<instances> >
@param param: Parameters for the training procedure
@type param: ParameterSvm
"""
# split for training weak_learners and boosting
(train_weak, train_boosting) = split_data(train_data, 4)
# merge data sets
data = PreparedMultitaskData(train_weak, shuffle=True)
# create shogun label
lab = shogun_factory.create_labels(data.labels)
########################################################
print "creating a kernel:"
########################################################
# init seq handler
pseudoseqs = SequencesHandler()
classifiers = []
for pocket in pockets:
print "creating normalizer"
#import pdb
#pdb.set_trace()
normalizer = MultitaskKernelNormalizer(data.task_vector_nums)
print "processing pocket", pocket
# set similarity
for task_name_lhs in data.get_task_names():
for task_name_rhs in data.get_task_names():
similarity = 0.0
for pseudo_seq_pos in pocket:
similarity += float(pseudoseqs.get_similarity(task_name_lhs, task_name_rhs, pseudo_seq_pos-1))
# normalize
similarity = similarity / float(len(pocket))
print "pocket %s (%s, %s) = %f" % (str(pocket), task_name_lhs, task_name_rhs, similarity)
normalizer.set_task_similarity(data.name_to_id(task_name_lhs), data.name_to_id(task_name_rhs), similarity)
print "creating empty kernel"
kernel = shogun_factory.create_kernel(data.examples, param)
print "setting normalizer"
kernel.set_normalizer(normalizer)
print "training SVM for pocket", pocket
svm = self._train_single_svm(param, kernel, lab)
classifiers.append(svm)
print "done obtaining weak learners"
# save additional info
#self.additional_information["svm_objective"] = svm.get_objective()
#self.additional_information["svm num sv"] = svm.get_num_support_vectors()
#self.additional_information["post_weights"] = combined_kernel.get_subkernel_weights()
#print self.additional_information
##################################################
# combine weak learners for each task
##################################################
# set constants
some = 0.9
import cvxmod
# wrap up predictors
svms = {}
# use a reference to the same svm several times
for task_name in train_boosting.keys():
instances = train_boosting[task_name]
N = len(instances)
F = len(pockets)
examples = [inst.example for inst in instances]
labels = [inst.label for inst in instances]
# dim = (F x N)
out = cvxmod.zeros((N,F))
for i in xrange(F):
svm = classifiers[i]
tmp_out = self._predict_weak(svm, examples, data.name_to_id(task_name))
out[:,i] = numpy.sign(tmp_out)
#out[:,i] = tmp_out
#TODO: fix
helper.save("/tmp/out_sparse", (out,labels))
pdb.set_trace()
weights = solve_boosting(out, labels, some, solver="mosek")
svms[task_name] = (data.name_to_id(task_name), svm)
return svms
