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 train_splice_predictor(examples, labels, param):
"""
@param examples: list of strings
@param labels: list of integers {-1,1}
"""
##########################
# build classifier
##########################
feat_train = create_hashed_features_wdk(param.flags, examples)
lab = create_labels(labels)
svm = create_svm(param, feat_train, lab)
svm.train()
return svm
def init_predictor(examples, labels, param, w):
"""
@param examples: list of strings
@param labels: list of integers {-1,1}
@param w: weight vector of trained svm
"""
##########################
# build classifier
##########################
feat_train = create_hashed_features_wdk(param.flags, examples)
lab = create_labels(labels)
svm = create_svm(param, feat_train, lab)
svm.set_w(w)
return svm
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 _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
"""
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 _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