Python SVMLight.set_linadd_enabled方法代码示例

# 需要导入模块: from shogun.Classifier import SVMLight [as 别名]
# 或者: from shogun.Classifier.SVMLight import set_linadd_enabled [as 别名]
    def _train_single_svm(self, param, kernel, lab):
    

    
        kernel.set_cache_size(500)
        #lab = shogun_factory.create_labels(data.labels) 
        svm = SVMLight(param.cost, 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)
            
        # 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()

        return svm

# 需要导入模块: from shogun.Classifier import SVMLight [as 别名]
# 或者: from shogun.Classifier.SVMLight import set_linadd_enabled [as 别名]
def do_batch_linadd ():
	print 'SVMlight batch'

	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)

	C=1
	epsilon=1e-5
	num_threads=2
	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.classify().get_labels()

	svm.set_batch_computation_enabled(True)
	svm.classify().get_labels()

# 需要导入模块: from shogun.Classifier import SVMLight [as 别名]
# 或者: from shogun.Classifier.SVMLight import set_linadd_enabled [as 别名]
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

# 需要导入模块: from shogun.Classifier import SVMLight [as 别名]
# 或者: from shogun.Classifier.SVMLight import set_linadd_enabled [as 别名]
            
##################################################################
# 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()

# 需要导入模块: from shogun.Classifier import SVMLight [as 别名]
# 或者: from shogun.Classifier.SVMLight import set_linadd_enabled [as 别名]
    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 = {}
#.........这里部分代码省略.........

# 需要导入模块: from shogun.Classifier import SVMLight [as 别名]
# 或者: from shogun.Classifier.SVMLight import set_linadd_enabled [as 别名]

#.........这里部分代码省略.........
    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"

# 需要导入模块: from shogun.Classifier import SVMLight [as 别名]
# 或者: from shogun.Classifier.SVMLight import set_linadd_enabled [as 别名]
    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