Python modshogun.RealFeatures类代码示例

def features_dense_modular (A=matrixA,B=matrixB,C=matrixC):

    a=RealFeatures(A)
    b=LongIntFeatures(B)
    c=ByteFeatures(C)

# or 16bit wide ...
#feat1 = f.ShortFeatures(N.zeros((10,5),N.short))
#feat2 = f.WordFeatures(N.zeros((10,5),N.uint16))


# print(some statistics about a)

# get first feature vector and set it

    a.set_feature_vector(array([1,4,0,0,0,9], dtype=float64), 0)

# get matrices
    a_out = a.get_feature_matrix()
    b_out = b.get_feature_matrix()
    c_out = c.get_feature_matrix()

    assert(all(a_out==A))

    assert(all(b_out==B))

    assert(all(c_out==C))
    return a_out,b_out,c_out,a,b,c

def transfer_multitask_clustered_logistic_regression (fm_train=traindat,fm_test=testdat,label_train=label_traindat):
	from modshogun import BinaryLabels, RealFeatures, Task, TaskGroup, MSG_DEBUG
	try:
		from modshogun import MultitaskClusteredLogisticRegression
	except ImportError:
		print("MultitaskClusteredLogisticRegression not available")
		exit()

	features = RealFeatures(hstack((traindat,sin(traindat),cos(traindat))))
	labels = BinaryLabels(hstack((label_train,label_train,label_train)))

	n_vectors = features.get_num_vectors()
	task_one = Task(0,n_vectors//3)
	task_two = Task(n_vectors//3,2*n_vectors//3)
	task_three = Task(2*n_vectors//3,n_vectors)
	task_group = TaskGroup()
	task_group.append_task(task_one)
	task_group.append_task(task_two)
	task_group.append_task(task_three)

	mtlr = MultitaskClusteredLogisticRegression(1.0,100.0,features,labels,task_group,2)
	#mtlr.io.set_loglevel(MSG_DEBUG)
	mtlr.set_tolerance(1e-3) # use 1e-2 tolerance
	mtlr.set_max_iter(100)
	mtlr.train()
	mtlr.set_current_task(0)
	#print mtlr.get_w()
	out = mtlr.apply_regression().get_labels()

	return out

def classifier_featureblock_logistic_regression (fm_train=traindat,fm_test=testdat,label_train=label_traindat):

	from modshogun import BinaryLabels, RealFeatures, IndexBlock, IndexBlockGroup
	try:
		from modshogun import FeatureBlockLogisticRegression
	except ImportError:
		print("FeatureBlockLogisticRegression not available")
		exit(0)

	features = RealFeatures(hstack((traindat,traindat)))
	labels = BinaryLabels(hstack((label_train,label_train)))

	n_features = features.get_num_features()
	block_one = IndexBlock(0,n_features//2)
	block_two = IndexBlock(n_features//2,n_features)
	block_group = IndexBlockGroup()
	block_group.add_block(block_one)
	block_group.add_block(block_two)

	mtlr = FeatureBlockLogisticRegression(0.1,features,labels,block_group)
	mtlr.set_regularization(1) # use regularization ratio
	mtlr.set_tolerance(1e-2) # use 1e-2 tolerance
	mtlr.train()
	out = mtlr.apply().get_labels()

	return out

def features_dense_io_modular():
	from modshogun import RealFeatures, CSVFile
	feats=RealFeatures()
	f=CSVFile("../data/fm_train_real.dat","r")
	f.set_delimiter(" ")
	feats.load(f)
	return feats

def transfer_multitask_leastsquares_regression (fm_train=traindat,fm_test=testdat,label_train=label_traindat):
	from modshogun import RegressionLabels, RealFeatures, Task, TaskGroup
	try:
		from modshogun import MultitaskLeastSquaresRegression
	except ImportError:
		print("MultitaskLeastSquaresRegression not available")
		exit(0)

	features = RealFeatures(traindat)
	labels = RegressionLabels(label_train)

	n_vectors = features.get_num_vectors()
	task_one = Task(0,n_vectors//2)
	task_two = Task(n_vectors//2,n_vectors)
	task_group = TaskGroup()
	task_group.append_task(task_one)
	task_group.append_task(task_two)

	mtlsr = MultitaskLeastSquaresRegression(0.1,features,labels,task_group)
	mtlsr.set_regularization(1) # use regularization ratio
	mtlsr.set_tolerance(1e-2) # use 1e-2 tolerance
	mtlsr.train()
	mtlsr.set_current_task(0)
	out = mtlsr.apply_regression().get_labels()
	return out

def transfer_multitask_l12_logistic_regression (fm_train=traindat,fm_test=testdat,label_train=label_traindat):
	from modshogun import BinaryLabels, RealFeatures, Task, TaskGroup
	try:
		from modshogun import MultitaskL12LogisticRegression
	except ImportError:
		print("MultitaskL12LogisticRegression not available")
		exit(0)

	features = RealFeatures(hstack((traindat,traindat)))
	labels = BinaryLabels(hstack((label_train,label_train)))

	n_vectors = features.get_num_vectors()
	task_one = Task(0,n_vectors//2)
	task_two = Task(n_vectors//2,n_vectors)
	task_group = TaskGroup()
	task_group.append_task(task_one)
	task_group.append_task(task_two)

	mtlr = MultitaskL12LogisticRegression(0.1,0.1,features,labels,task_group)
	mtlr.set_tolerance(1e-2) # use 1e-2 tolerance
	mtlr.set_max_iter(10)
	mtlr.train()
	mtlr.set_current_task(0)
	out = mtlr.apply_regression().get_labels()

	return out

def features_dense_zero_copy_modular (in_data=data):
	feats = None
	if numpy.__version__ >= '1.5':
		feats=numpy.array(in_data, dtype=float64, order='F')

		a=RealFeatures()
		a.frombuffer(feats, False)

		b=numpy.array(a, copy=False)
		c=numpy.array(a, copy=True)

		d=RealFeatures()
		d.frombuffer(a, False)

		e=RealFeatures()
		e.frombuffer(a, True)

		a[:,0]=0
		#print a[0:4]
		#print b[0:4]
		#print c[0:4]
		#print d[0:4]
		#print e[0:4]
	else:
		print("numpy version >= 1.5 is needed")

	return feats

def modelselection_grid_search_kernel (num_subsets, num_vectors, dim_vectors):
	# init seed for reproducability
	Math.init_random(1)
	random.seed(1);

	# create some (non-sense) data
	matrix=random.rand(dim_vectors, num_vectors)

	# create num_feautres 2-dimensional vectors
	features=RealFeatures()
	features.set_feature_matrix(matrix)

	# create labels, two classes
	labels=BinaryLabels(num_vectors)
	for i in range(num_vectors):
		labels.set_label(i, 1 if i%2==0 else -1)

	# create svm
	classifier=LibSVM()

	# splitting strategy
	splitting_strategy=StratifiedCrossValidationSplitting(labels, num_subsets)

	# accuracy evaluation
	evaluation_criterion=ContingencyTableEvaluation(ACCURACY)

	# cross validation class for evaluation in model selection
	cross=CrossValidation(classifier, features, labels, splitting_strategy, evaluation_criterion)
	cross.set_num_runs(1)

	# print all parameter available for modelselection
	# Dont worry if yours is not included, simply write to the mailing list
	#classifier.print_modsel_params()

	# model parameter selection
	param_tree=create_param_tree()
	#param_tree.print_tree()

	grid_search=GridSearchModelSelection(cross, param_tree)

	print_state=False
	best_combination=grid_search.select_model(print_state)
	#print("best parameter(s):")
	#best_combination.print_tree()

	best_combination.apply_to_machine(classifier)

	# larger number of runs to have tighter confidence intervals
	cross.set_num_runs(10)
	cross.set_conf_int_alpha(0.01)
	result=cross.evaluate()
	casted=CrossValidationResult.obtain_from_generic(result);
	#print "result mean:", casted.mean

	return classifier,result,casted.mean

def features_dense_real_modular (A=matrix):

# ... of type Real, LongInt and Byte
    a=RealFeatures(A)

# print(some statistics about a)
#print(a.get_num_vectors())
#print(a.get_num_features())

# get first feature vector and set it
#print(a.get_feature_vector(0))
    a.set_feature_vector(array([1,4,0,0,0,9], dtype=float64), 0)

# get matrix
    a_out = a.get_feature_matrix()

    assert(all(a_out==A))
    return a_out

def multiclass_c45classifiertree_modular(train=traindat,test=testdat,labels=label_traindat,ft=feattypes):
	try:
		from modshogun import RealFeatures, MulticlassLabels, CSVFile, C45ClassifierTree
		from numpy import random, int32
	except ImportError:
		print("Could not import Shogun and/or numpy modules")
		return

	# wrap features and labels into Shogun objects
	feats_train=RealFeatures(CSVFile(train))
	feats_test=RealFeatures(CSVFile(test))
	train_labels=MulticlassLabels(CSVFile(labels))

	# divide train dataset into training and validation subsets in the ratio 2/3 to 1/3
	subset=int32(random.permutation(feats_train.get_num_vectors()))
	vsubset=subset[1:subset.size/3]
	trsubset=subset[1+subset.size/3:subset.size]

	# C4.5 Tree formation using training subset
	train_labels.add_subset(trsubset)
	feats_train.add_subset(trsubset)

	c=C45ClassifierTree()
	c.set_labels(train_labels)
	c.set_feature_types(ft)
	c.train(feats_train)

	train_labels.remove_subset()
	feats_train.remove_subset()

	# prune tree using validation subset
	train_labels.add_subset(vsubset)
	feats_train.add_subset(vsubset)

	c.prune_tree(feats_train,train_labels)

	train_labels.remove_subset()
	feats_train.remove_subset()

	# Classify test data
	output=c.apply_multiclass(feats_test).get_labels()
	output_certainty=c.get_certainty_vector()

	return c,output,output_certainty

def transfer_multitask_group_regression(fm_train=traindat,fm_test=testdat,label_train=label_traindat):

	from modshogun import RegressionLabels, RealFeatures, Task, TaskGroup, MultitaskLSRegression

	features = RealFeatures(traindat)
	labels = RegressionLabels(label_train)

	n_vectors = features.get_num_vectors()
	task_one = Task(0,n_vectors/2)
	task_two = Task(n_vectors/2,n_vectors)
	task_group = TaskGroup()
	task_group.add_task(task_one)
	task_group.add_task(task_two)

	mtlsr = MultitaskLSRegression(0.1,features,labels,task_group)
	mtlsr.train()
	mtlsr.set_current_task(0)
	out = mtlsr.apply_regression().get_labels()
	return out

def neuralnets_simple_modular (train_fname, test_fname,
		label_fname, C, epsilon):

	from modshogun import NeuralLayers, NeuralNetwork, RealFeatures, BinaryLabels
	from modshogun import Math_init_random, CSVFile
	Math_init_random(17)

	feats_train=RealFeatures(CSVFile(train_fname))
	feats_test=RealFeatures(CSVFile(test_fname))
	labels=BinaryLabels(CSVFile(label_fname))

	layers = NeuralLayers()
	network = NeuralNetwork(layers.input(feats_train.get_num_features()).linear(50).softmax(2).done())
	network.quick_connect()
	network.initialize_neural_network()

	network.set_labels(labels)
	network.train(feats_train)
	return network, network.apply_multiclass(feats_test)

def load_data(num_train_samples=7291, m_data_dict=data_dict):
	from modshogun import RealFeatures, MulticlassLabels
	import numpy

	train_vec = m_data_dict['yTr'][0][:num_train_samples].astype(numpy.float64)
	train_labels = MulticlassLabels(train_vec)
	test_vec = m_data_dict['yTe'][0].astype(numpy.float64)
 	test_labels = MulticlassLabels(test_vec)
	print "#train_labels = " + str(train_labels.get_num_labels())
	print "#test_labels  = " + str(test_labels.get_num_labels())

	train_mat = m_data_dict['xTr'][:,:num_train_samples].astype(numpy.float64)
	train_features = RealFeatures(train_mat)
	test_mat = m_data_dict['xTe'].astype(numpy.float64)
	test_features = RealFeatures(test_mat)
	print "#train_vectors = " + str(train_features.get_num_vectors())
	print "#test_vectors  = " + str(test_features.get_num_vectors())
	print "data dimension = " + str(test_features.get_num_features())

	return train_features, train_labels, test_features, test_labels

def preprocessor_prunevarsubmean_modular (fm_train_real=traindat,fm_test_real=testdat,width=1.4,size_cache=10):
	from modshogun import Chi2Kernel
	from modshogun import RealFeatures
	from modshogun import PruneVarSubMean

	feats_train=RealFeatures(fm_train_real)
	feats_test=RealFeatures(fm_test_real)

	preproc=PruneVarSubMean()
	preproc.init(feats_train)
	feats_train.add_preprocessor(preproc)
	feats_train.apply_preprocessor()
	feats_test.add_preprocessor(preproc)
	feats_test.apply_preprocessor()

	kernel=Chi2Kernel(feats_train, feats_train, width, size_cache)

	km_train=kernel.get_kernel_matrix()
	kernel.init(feats_train, feats_test)
	km_test=kernel.get_kernel_matrix()

	return km_train,km_test,kernel

def transfer_multitask_logistic_regression (fm_train=traindat,fm_test=testdat,label_train=label_traindat):

	from modshogun import BinaryLabels, RealFeatures, Task, TaskGroup, MultitaskLogisticRegression

	features = RealFeatures(hstack((traindat,traindat)))
	labels = BinaryLabels(hstack((label_train,label_train)))

	n_vectors = features.get_num_vectors()
	task_one = Task(0,n_vectors/2)
	task_two = Task(n_vectors/2,n_vectors)
	task_group = TaskGroup()
	task_group.append_task(task_one)
	task_group.append_task(task_two)

	mtlr = MultitaskLogisticRegression(0.1,features,labels,task_group)
	mtlr.set_regularization(1) # use regularization ratio
	mtlr.set_tolerance(1e-2) # use 1e-2 tolerance
	mtlr.train()
	mtlr.set_current_task(0)
	out = mtlr.apply().get_labels()

	return out