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_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 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 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 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 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 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 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 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_randomfouriergausspreproc_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 RandomFourierGaussPreproc feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) preproc=RandomFourierGaussPreproc() 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
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 metric_lmnn_statistics(
k=3,
fname_features="../../data/fm_train_multiclass_digits.dat.gz",
fname_labels="../../data/label_train_multiclass_digits.dat",
):
try:
from modshogun import LMNN, CSVFile, RealFeatures, MulticlassLabels, MSG_DEBUG
import matplotlib.pyplot as pyplot
except ImportError:
print "Error importing modshogun or other required modules. Please, verify their installation."
return
features = RealFeatures(load_compressed_features(fname_features).T)
labels = MulticlassLabels(CSVFile(fname_labels))
# print 'number of examples = %d' % features.get_num_vectors()
# print 'number of features = %d' % features.get_num_features()
assert features.get_num_vectors() == labels.get_num_labels()
# train LMNN
lmnn = LMNN(features, labels, k)
lmnn.set_correction(100)
# lmnn.io.set_loglevel(MSG_DEBUG)
print "Training LMNN, this will take about two minutes..."
lmnn.train()
print "Training done!"
# plot objective obtained during training
statistics = lmnn.get_statistics()
pyplot.plot(statistics.obj.get())
pyplot.grid(True)
pyplot.xlabel("Iterations")
pyplot.ylabel("LMNN objective")
pyplot.title("LMNN objective during training for the multiclass digits data set")
pyplot.show()
def train(self, images, labels):
"""
Train eigenfaces
"""
print "Train...",
#copy labels
self._labels = labels;
#transform the numpe vector to shogun structure
features = RealFeatures(images)
#PCA
self.pca = PCA()
#set dimension
self.pca.set_target_dim(self._num_components);
#compute PCA
self.pca.init(features)
for sampleIdx in range(features.get_num_vectors()):
v = features.get_feature_vector(sampleIdx);
p = self.pca.apply_to_feature_vector(v);
self._projections.insert(sampleIdx, p);
print "ok!"
def preprocessor_normone_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 NormOne feats_train=RealFeatures(fm_train_real) feats_test=RealFeatures(fm_test_real) preprocessor=NormOne() preprocessor.init(feats_train) feats_train.add_preprocessor(preprocessor) feats_train.apply_preprocessor() feats_test.add_preprocessor(preprocessor) 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 preprocessor_fisherlda_modular (data, labels, method):
from modshogun import RealFeatures, MulticlassLabels, CANVAR_FLDA
from modshogun import FisherLda
from modshogun import MulticlassLabels
sg_features = RealFeatures(data)
sg_labels = MulticlassLabels(labels)
preprocessor=FisherLda(method)
preprocessor.init(sg_features, sg_labels, 1)
yn=preprocessor.apply_to_feature_matrix(sg_features)
return yn
def fit(self, X, y):
self.X_, y = check_X_y(X, y, dtype=float)
labels = MulticlassLabels(y)
self._lmnn = shogun_LMNN(RealFeatures(self.X_.T), labels, self.k)
self._lmnn.set_maxiter(self.max_iter)
self._lmnn.set_obj_threshold(self.convergence_tol)
self._lmnn.set_regularization(self.regularization)
self._lmnn.set_stepsize(self.learn_rate)
if self.use_pca:
self._lmnn.train()
else:
self._lmnn.train(np.eye(X.shape[1]))
self.L_ = self._lmnn.get_linear_transform()
return self
def run_clustering(data, k):
from modshogun import KMeans
from modshogun import Math_init_random
from modshogun import EuclideanDistance
from modshogun import RealFeatures
fea = RealFeatures(data)
distance = EuclideanDistance(fea, fea)
kmeans = KMeans(k, distance)
#print("Running clustering...")
kmeans.train()
return kmeans.get_cluster_centers()
def transfer_multitask_leastsquares_regression(fm_train=traindat,
fm_test=testdat,
label_train=label_traindat):
from modshogun import RegressionLabels, RealFeatures, Task, TaskGroup, MultitaskLeastSquaresRegression
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 RunSVMShogun(q):
totalTimer = Timer()
Log.Info("Loading dataset", self.verbose)
trainData, labels = SplitTrainData(self.dataset)
trainData = RealFeatures(trainData.T)
labels = MulticlassLabels(labels)
testData = RealFeatures(LoadDataset(self.dataset[1]).T)
try:
with totalTimer:
self.model = self.BuildModel(trainData, labels, options)
# Run Support vector machines on the test dataset.
self.model.apply(testData).get_labels()
except Exception as e:
Log.Debug(str(e))
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def converter_localitypreservingprojections_modular(data_fname, k):
try:
from modshogun import RealFeatures, LocalityPreservingProjections, CSVFile
features = RealFeatures(CSVFile(data_fname))
converter = LocalityPreservingProjections()
converter.set_target_dim(1)
converter.set_k(k)
converter.set_tau(2.0)
converter.apply(features)
return features
except ImportError:
print('No Eigen3 available')
def classifier_libsvm_modular(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from modshogun import RealFeatures, BinaryLabels
from modshogun import GaussianKernel, LibSVM, CSVFile
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = BinaryLabels(CSVFile(label_fname))
kernel = GaussianKernel(feats_train, feats_train, width)
svm = LibSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
supportvectors = sv_idx = svm.get_support_vectors()
alphas = svm.get_alphas()
predictions = svm.apply(feats_test)
#print predictions.get_labels()
return predictions, svm, predictions.get_labels()
def classifier_svmlin_modular(train_fname=traindat,
test_fname=testdat,
label_fname=label_traindat,
C=0.9,
epsilon=1e-5,
num_threads=1):
from modshogun import RealFeatures, SparseRealFeatures, BinaryLabels
from modshogun import SVMLin, CSVFile
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
labels = BinaryLabels(CSVFile(label_fname))
svm = SVMLin(C, feats_train, labels)
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.set_bias_enabled(True)
svm.train()
bias = svm.get_bias()
w = svm.get_w()
predictions = svm.apply(feats_test)
return predictions, svm, predictions.get_labels()
def classifier_featureblock_logistic_regression(fm_train=traindat,
fm_test=testdat,
label_train=label_traindat):
from modshogun import BinaryLabels, RealFeatures, IndexBlock, IndexBlockGroup, FeatureBlockLogisticRegression
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 train(self, images, labels):
"""
Train eigenfaces
"""
print "Train..."
#copy labels
self._labels = labels
#transform the numpe vector to shogun structure
features = RealFeatures(images)
#PCA
self.pca = PCA()
#set dimension
self.pca.set_target_dim(self._num_components)
#compute PCA
self.pca.init(features)
for sampleIdx in range(features.get_num_vectors()):
v = features.get_feature_vector(sampleIdx)
p = self.pca.apply_to_feature_vector(v)
self._projections.insert(sampleIdx, p)
print "Train ok!"
def RunKNCShogun():
totalTimer = Timer()
Log.Info("Loading dataset", self.verbose)
trainData, labels = SplitTrainData(self.dataset)
trainData = RealFeatures(trainData.T)
labels = MulticlassLabels(labels)
testData = RealFeatures(LoadDataset(self.dataset[1]).T)
try:
with totalTimer:
self.model = self.BuildModel(trainData, labels, options)
# Run the k-nearest neighbors Classifier on the test dataset.
self.predictions = self.model.apply_multiclass(
testData).get_labels()
except Exception as e:
return [-1]
time = totalTimer.ElapsedTime()
if len(self.dataset) > 1:
return [time, self.predictions]
return [time]
def converter_isomap_modular(data_fname):
try:
from modshogun import RealFeatures, Isomap, CSVFile
features = RealFeatures(CSVFile(data))
converter = Isomap()
converter.set_k(20)
converter.set_target_dim(1)
converter.apply(features)
return features
except ImportError:
print('No Eigen3 available')
def clustering_kmeans_modular (fm_train=traindat,k=3): from modshogun import EuclideanDistance, RealFeatures, KMeans, Math_init_random, CSVFile Math_init_random(17) feats_train=RealFeatures(CSVFile(fm_train)) distance=EuclideanDistance(feats_train, feats_train) kmeans=KMeans(k, distance) kmeans.train() out_centers = kmeans.get_cluster_centers() kmeans.get_radiuses() return out_centers, kmeans
def converter_linearlocaltangentspacealignment_modular(data_fname, k):
try:
from modshogun import RealFeatures, LinearLocalTangentSpaceAlignment, CSVFile
features = RealFeatures(CSVFile(data_fname))
converter = LinearLocalTangentSpaceAlignment()
converter.set_target_dim(1)
converter.set_k(k)
converter.apply(features)
return features
except ImportError:
print('No Eigen3 available')
def RunMetrics(self, options):
if len(self.dataset) >= 3:
X, y = SplitTrainData(self.dataset)
tau = re.search("-t (\d+)", options)
tau = 1.0 if not tau else int(tau.group(1))
model = LRR(tau, RealFeatures(X.T), RegressionLabels(y))
model.train()
testData = LoadDataset(self.dataset[1])
truelabels = LoadDataset(self.dataset[2])
predictedlabels = model.apply_regression(RealFeatures(
testData.T)).get_labels()
SimpleMSE = Metrics.SimpleMeanSquaredError(truelabels,
predictedlabels)
metrics_dict = {}
metrics_dict['Simple MSE'] = SimpleMSE
return metrics_dict
else:
Log.Fatal("This method requires three datasets!")
def classifier_multilabeloutputliblinear_modular(
fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
label_test_multiclass=label_testdat,
width=2.1,
C=1,
epsilon=1e-5):
from modshogun import RealFeatures, MulticlassLabels, MultilabelLabels
from modshogun import MulticlassLibLinear
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
labels = MulticlassLabels(label_train_multiclass)
classifier = MulticlassLibLinear(C, feats_train, labels)
classifier.train()
label_pred = classifier.apply_multilabel_output(feats_test, 2)
out = label_pred.get_labels()
#print out
return out
def converter_hessianlocallylinearembedding_modular(data_fname, k):
try:
from modshogun import RealFeatures, HessianLocallyLinearEmbedding, CSVFile
features = RealFeatures(CSVFile(data))
converter = HessianLocallyLinearEmbedding()
converter.set_target_dim(1)
converter.set_k(k)
converter.apply(features)
return features
except ImportError:
print('No Eigen3 available')
def RunMetrics(self, options):
Log.Info("Perform Linear Ridge Regression.", self.verbose)
results = self.LinearRidgeRegressionShogun(options)
if results < 0:
return results
metrics = {'Runtime': results}
if len(self.dataset) >= 3:
X, y = SplitTrainData(self.dataset)
if "alpha" in options:
tau = float(options.pop("alpha"))
else:
Log.Fatal("Required parameter 'alpha' not specified!")
raise Exception("missing parameter")
if len(options) > 0:
Log.Fatal("Unknown parameters: " + str(options))
raise Exception("unknown parameters")
model = LRR(tau, RealFeatures(X.T), RegressionLabels(y))
model.train()
testData = LoadDataset(self.dataset[1])
truelabels = LoadDataset(self.dataset[2])
predictedlabels = model.apply_regression(RealFeatures(
testData.T)).get_labels()
SimpleMSE = Metrics.SimpleMeanSquaredError(truelabels,
predictedlabels)
metrics['Simple MSE'] = SimpleMSE
return metrics
else:
Log.Fatal("This method requires three datasets!")
def converter_laplacianeigenmaps_modular (data_fname,k):
try:
from modshogun import RealFeatures, LaplacianEigenmaps, CSVFile
features = RealFeatures(CSVFile(data_fname))
converter = LaplacianEigenmaps()
converter.set_target_dim(1)
converter.set_k(k)
converter.set_tau(20.0)
converter.apply(features)
return features
except ImportError:
print('No Eigen3 available')
def preprocessor_dimensionreductionpreprocessor_modular (data, k): from modshogun import RealFeatures from modshogun import DimensionReductionPreprocessor from modshogun import LocallyLinearEmbedding features = RealFeatures(data) converter = LocallyLinearEmbedding() converter.set_k(k) preprocessor = DimensionReductionPreprocessor(converter) preprocessor.init(features) preprocessor.apply_to_feature_matrix(features) return features
def multiclass_chaidtree_modular(train=traindat,
test=testdat,
labels=label_traindat,
ft=feattypes):
try:
from modshogun import RealFeatures, MulticlassLabels, CSVFile, CHAIDTree
except ImportError:
print("Could not import Shogun modules")
return
# wrap features and labels into Shogun objects
feats_train = RealFeatures(CSVFile(train))
feats_test = RealFeatures(CSVFile(test))
train_labels = MulticlassLabels(CSVFile(labels))
# CHAID Tree formation with nominal dependent variable
c = CHAIDTree(0, feattypes, 10)
c.set_labels(train_labels)
c.train(feats_train)
# Classify test data
output = c.apply_multiclass(feats_test).get_labels()
return c, output
def regression_randomforest_modular(num_train=500,
num_test=50,
x_range=15,
noise_var=0.2,
ft=feattypes):
try:
from modshogun import RealFeatures, RegressionLabels, CSVFile, RandomForest, MeanRule, PT_REGRESSION
except ImportError:
print("Could not import Shogun modules")
return
random.seed(1)
# form training dataset : y=x with noise
X_train = random.rand(1, num_train) * x_range
Y_train = X_train + random.randn(num_train) * noise_var
# form test dataset
X_test = array([[float(i) / num_test * x_range for i in range(num_test)]])
# wrap features and labels into Shogun objects
feats_train = RealFeatures(X_train)
feats_test = RealFeatures(X_test)
train_labels = RegressionLabels(Y_train[0])
# Random Forest formation
rand_forest = RandomForest(feats_train, train_labels, 20, 1)
rand_forest.set_feature_types(ft)
rand_forest.set_machine_problem_type(PT_REGRESSION)
rand_forest.set_combination_rule(MeanRule())
rand_forest.train()
# Regress test data
output = rand_forest.apply_regression(feats_test).get_labels()
return rand_forest, output
def fit(self, X, labels):
self.X = X
self.L = np.eye(X.shape[1])
labels = MulticlassLabels(labels.astype(np.float64))
self._lmnn = shogun_LMNN(RealFeatures(X.T), labels, self.params['k'])
self._lmnn.set_maxiter(self.params['max_iter'])
self._lmnn.set_obj_threshold(self.params['convergence_tol'])
self._lmnn.set_regularization(self.params['regularization'])
self._lmnn.set_stepsize(self.params['learn_rate'])
if self.params['use_pca']:
self._lmnn.train()
else:
self._lmnn.train(self.L)
self.L = self._lmnn.get_linear_transform()
return self
def kernel_io_modular(train_fname=traindat, test_fname=testdat, width=1.9):
from modshogun import RealFeatures, GaussianKernel, CSVFile
feats_train = RealFeatures(CSVFile(train_fname))
feats_test = RealFeatures(CSVFile(test_fname))
kernel = GaussianKernel(feats_train, feats_train, width)
km_train = kernel.get_kernel_matrix()
f = CSVFile("tmp/gaussian_train.csv", "w")
kernel.save(f)
del f
kernel.init(feats_train, feats_test)
km_test = kernel.get_kernel_matrix()
f = CSVFile("tmp/gaussian_test.csv", "w")
kernel.save(f)
del f
#clean up
import os
os.unlink("tmp/gaussian_test.csv")
os.unlink("tmp/gaussian_train.csv")
return km_train, km_test, kernel
def fit(self, X, y):
X, y = self._prepare_inputs(X, y, dtype=float,
ensure_min_samples=2)
labels = MulticlassLabels(y)
self._lmnn = shogun_LMNN(RealFeatures(X.T), labels, self.k)
self._lmnn.set_maxiter(self.max_iter)
self._lmnn.set_obj_threshold(self.convergence_tol)
self._lmnn.set_regularization(self.regularization)
self._lmnn.set_stepsize(self.learn_rate)
if self.use_pca:
self._lmnn.train()
else:
self._lmnn.train(np.eye(X.shape[1]))
self.transformer_ = self._lmnn.get_linear_transform(X)
return self
def classifier_multiclasslibsvm_modular(fm_train_real=traindat,
fm_test_real=testdat,
label_train_multiclass=label_traindat,
width=2.1,
C=1,
epsilon=1e-5):
from modshogun import RealFeatures, MulticlassLabels
from modshogun import GaussianKernel
from modshogun import MulticlassLibSVM
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
kernel = GaussianKernel(feats_train, feats_train, width)
labels = MulticlassLabels(label_train_multiclass)
svm = MulticlassLibSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
kernel.init(feats_train, feats_test)
out = svm.apply().get_labels()
predictions = svm.apply()
return predictions, svm, predictions.get_labels()
def RunLinearRegressionShogun(q):
totalTimer = Timer()
# Load input dataset.
# If the dataset contains two files then the second file is the responses
# file.
try:
Log.Info("Loading dataset", self.verbose)
if len(self.dataset) == 2:
testSet = np.genfromtxt(self.dataset[1], delimiter=',')
# Use the last row of the training set as the responses.
X, y = SplitTrainData(self.dataset)
if len(options) > 0:
Log.Fatal("Unknown parameters: " + str(options))
raise Exception("unknown parameters")
with totalTimer:
# Perform linear regression.
model = LeastSquaresRegression(RealFeatures(X.T),
RegressionLabels(y))
model.train()
b = model.get_w()
if len(self.dataset) == 2:
pred = classifier.apply(RealFeatures(testSet.T))
self.predictions = pred.get_labels()
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def compute_output_plot_isolines_sine(classifier,
kernel,
train,
regression=False):
x = 4 * rand(1, 500) - 2
x.sort()
test = RealFeatures(x)
kernel.init(train, test)
if regression:
y = classifier.apply().get_labels()
else:
y = classifier.apply().get_values()
return x, y
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
def converter_diffusionmaps_modular(data_fname, t):
try:
from modshogun import RealFeatures, DiffusionMaps, GaussianKernel, CSVFile
features = RealFeatures(CSVFile(data_fname))
converter = DiffusionMaps()
converter.set_target_dim(1)
converter.set_kernel(GaussianKernel(10, 10.0))
converter.set_t(t)
converter.apply(features)
return features
except ImportError:
print('No Eigen3 available')
def stochasticgbmachine_modular(train=traindat,train_labels=label_traindat,ft=feat_types):
try:
from modshogun import RealFeatures, RegressionLabels, CSVFile, CARTree, StochasticGBMachine, SquaredLoss
except ImportError:
print("Could not import Shogun modules")
return
# wrap features and labels into Shogun objects
feats=RealFeatures(CSVFile(train))
labels=RegressionLabels(CSVFile(train_labels))
# divide into training (90%) and test dataset (10%)
p=np.random.permutation(labels.get_num_labels())
num=labels.get_num_labels()*0.9
cart=CARTree()
cart.set_feature_types(ft)
cart.set_max_depth(1)
loss=SquaredLoss()
s=StochasticGBMachine(cart,loss,500,0.01,0.6)
# train
feats.add_subset(np.int32(p[0:num]))
labels.add_subset(np.int32(p[0:num]))
s.set_labels(labels)
s.train(feats)
feats.remove_subset()
labels.remove_subset()
# apply
feats.add_subset(np.int32(p[num:len(p)]))
labels.add_subset(np.int32(p[num:len(p)]))
output=s.apply_regression(feats)
feats.remove_subset()
labels.remove_subset()
return s,output
def statistics_hsic (n, difference, angle): from modshogun import RealFeatures from modshogun import DataGenerator from modshogun import GaussianKernel from modshogun import HSIC from modshogun import BOOTSTRAP, HSIC_GAMMA from modshogun import EuclideanDistance from modshogun import Math, Statistics, IntVector # init seed for reproducability Math.init_random(1) # note that the HSIC has to store kernel matrices # which upper bounds the sample size # use data generator class to produce example data data=DataGenerator.generate_sym_mix_gauss(n,difference,angle) #plot(data[0], data[1], 'x');show() # create shogun feature representation features_x=RealFeatures(array([data[0]])) features_y=RealFeatures(array([data[1]])) # compute median data distance in order to use for Gaussian kernel width # 0.5*median_distance normally (factor two in Gaussian kernel) # However, shoguns kernel width is different to usual parametrization # Therefore 0.5*2*median_distance^2 # Use a subset of data for that, only 200 elements. Median is stable subset=IntVector.randperm_vec(features_x.get_num_vectors()) subset=subset[0:200] features_x.add_subset(subset) dist=EuclideanDistance(features_x, features_x) distances=dist.get_distance_matrix() features_x.remove_subset() median_distance=Statistics.matrix_median(distances, True) sigma_x=median_distance**2 features_y.add_subset(subset) dist=EuclideanDistance(features_y, features_y) distances=dist.get_distance_matrix() features_y.remove_subset() median_distance=Statistics.matrix_median(distances, True) sigma_y=median_distance**2 #print "median distance for Gaussian kernel on x:", sigma_x #print "median distance for Gaussian kernel on y:", sigma_y kernel_x=GaussianKernel(10,sigma_x) kernel_y=GaussianKernel(10,sigma_y) hsic=HSIC(kernel_x,kernel_y,features_x,features_y) # perform test: compute p-value and test if null-hypothesis is rejected for # a test level of 0.05 using different methods to approximate # null-distribution statistic=hsic.compute_statistic() #print "HSIC:", statistic alpha=0.05 #print "computing p-value using bootstrapping" hsic.set_null_approximation_method(BOOTSTRAP) # normally, at least 250 iterations should be done, but that takes long hsic.set_bootstrap_iterations(100) # bootstrapping allows usage of unbiased or biased statistic p_value_boot=hsic.compute_p_value(statistic) thresh_boot=hsic.compute_threshold(alpha) #print "p_value:", p_value_boot #print "threshold for 0.05 alpha:", thresh_boot #print "p_value <", alpha, ", i.e. test sais p and q are dependend:", p_value_boot<alpha #print "computing p-value using gamma method" hsic.set_null_approximation_method(HSIC_GAMMA) p_value_gamma=hsic.compute_p_value(statistic) thresh_gamma=hsic.compute_threshold(alpha) #print "p_value:", p_value_gamma #print "threshold for 0.05 alpha:", thresh_gamma #print "p_value <", alpha, ", i.e. test sais p and q are dependend::", p_value_gamma<alpha # sample from null distribution (these may be plotted or whatsoever) # mean should be close to zero, variance stronly depends on data/kernel # bootstrapping, biased statistic #print "sampling null distribution using bootstrapping" hsic.set_null_approximation_method(BOOTSTRAP) hsic.set_bootstrap_iterations(100) null_samples=hsic.bootstrap_null() #print "null mean:", mean(null_samples) #print "null variance:", var(null_samples) #hist(null_samples, 100); show() return p_value_boot, thresh_boot, p_value_gamma, thresh_gamma, statistic, null_samples
def predict_new_data(graph_file, cons_file, tri_file, other_feature_file):
print "reading extracted features"
graph_feature = read_feature_data(graph_file)
graph_feature = get_normalized_given_max_min(graph_feature, "models/grtaph_max_size")
cons_feature = read_feature_data(cons_file)
cons_feature = get_normalized_given_max_min(cons_feature, "models/cons_max_size")
CC_feature = read_feature_data(tri_file)
CC_feature = get_normalized_given_max_min(CC_feature, "models/tri_max_size")
ATOS_feature = read_feature_data(other_feature_file)
ATOS_feature = get_normalized_given_max_min(ATOS_feature, "models/alu_max_size")
width, C, epsilon, num_threads, mkl_epsilon, mkl_norm = 0.5, 1.2, 1e-5, 1, 0.001, 3.5
kernel = CombinedKernel()
feats_train = CombinedFeatures()
feats_test = CombinedFeatures()
# pdb.set_trace()
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(graph_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/graph.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(cons_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/cons.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(CC_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/tri.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
subkfeats_train = RealFeatures()
subkfeats_test = RealFeatures(np.transpose(np.array(ATOS_feature)))
subkernel = GaussianKernel(10, width)
feats_test.append_feature_obj(subkfeats_test)
fstream = SerializableAsciiFile("models/alu.dat", "r")
status = subkfeats_train.load_serializable(fstream)
feats_train.append_feature_obj(subkfeats_train)
kernel.append_kernel(subkernel)
model_file = "models/mkl.dat"
if not os.path.exists(model_file):
print "downloading model file"
url_add = "http://rth.dk/resources/mirnasponge/data/mkl.dat"
urllib.urlretrieve(url_add, model_file)
print "loading trained model"
fstream = SerializableAsciiFile("models/mkl.dat", "r")
new_mkl = MKLClassification()
status = new_mkl.load_serializable(fstream)
print "model predicting"
kernel.init(feats_train, feats_test)
new_mkl.set_kernel(kernel)
y_out = new_mkl.apply().get_labels()
return y_out
def plot_data(x,y,axis):
for idx,val in enumerate(numpy.unique(y)):
xi = x[y==val]
axis.scatter(xi[:,0], xi[:,1], s=50, facecolors='none', edgecolors=COLS[idx])
def plot_neighborhood_graph(x, nn, axis):
for i in xrange(x.shape[0]):
xs = [x[i,0], x[nn[1,i], 0]]
ys = [x[i,1], x[nn[1,i], 1]]
axis.plot(xs, ys, COLS[int(y[i])])
figure, axarr = pyplot.subplots(3, 1)
x, y = sandwich_data()
features = RealFeatures(x.T)
labels = MulticlassLabels(y)
print('%d vectors with %d features' % (features.get_num_vectors(), features.get_num_features()))
assert(features.get_num_vectors() == labels.get_num_labels())
distance = EuclideanDistance(features, features)
k = 2
knn = KNN(k, distance, labels)
plot_data(x, y, axarr[0])
plot_neighborhood_graph(x, knn.nearest_neighbors(), axarr[0])
axarr[0].set_aspect('equal')
axarr[0].set_xlim(-6, 4)
axarr[0].set_ylim(-3, 2)
knn = KNN(k, distance, train_labels)
knn.train()
test_features, test_labels = testdat.features, testdat.labels
predicted_labels = knn.apply(test_features)
evaluator = MulticlassAccuracy()
acc = evaluator.evaluate(predicted_labels, test_labels)
err = 1-acc
return err
features_file = '../data/fm_ape_gut.txt'
labels_file = '../data/label_ape_gut.txt'
features = RealFeatures(CSVFile(features_file))
labels = MulticlassLabels(CSVFile(labels_file))
# reduce the number of features to use so that the training is faster but still
# the results of feature selection are significant
fm = features.get_feature_matrix()
features = RealFeatures(fm[:500, :])
assert(features.get_num_vectors() == labels.get_num_labels())
print('Number of examples = %d, number of features = %d.' % (features.get_num_vectors(), features.get_num_features()))
visualize_tdsne(features, labels)
lmnn = diagonal_lmnn(features, labels, max_iter=1200)
diagonal_transform = lmnn.get_linear_transform()
#!/usr/bin/python
from scipy import io
data_dict = io.loadmat('../data/NBData20_train_preprocessed.mat')
xt = data_dict['xt']
yt = data_dict['yt']
import numpy
from modshogun import RealFeatures,MulticlassLabels,LMNN,MSG_DEBUG
features = RealFeatures(xt.T)
labels = MulticlassLabels(numpy.squeeze(yt))
k = 6
lmnn = LMNN(features,labels,k)
lmnn.io.set_loglevel(MSG_DEBUG)
lmnn.set_diagonal(True)
lmnn.set_maxiter(10000)
lmnn.train(numpy.eye(features.get_num_features()))
def feature_function():
from modshogun import RealFeatures
from modshogun import CSVFile
import numpy as np
#3x3 random matrix
feat_arr = np.random.rand(3, 3)
#initialize RealFeatures from numpy array
features = RealFeatures(feat_arr)
#get matrix value function
print features.get_feature_matrix(features)
#get selected column of matrix
print features.get_feature_vector(1)
#get number of columns
print features.get_num_features()
#get number of rows
print features.get_num_vectors()
feats_from_csv = RealFeatures(CSVFile("csv/feature.csv"))
print "csv is ", feats_from_csv.get_feature_matrix()
#!/usr/bin/env python2.7 # # This software is distributed under BSD 3-clause license (see LICENSE file). # # Copyright (C) 2014 Thoralf Klein # from modshogun import RealFeatures, BinaryLabels, LibLinear from numpy import random, mean X_train = RealFeatures(random.randn(30, 100)) Y_train = BinaryLabels(random.randn(X_train.get_num_vectors())) svm = LibLinear(1.0, X_train, Y_train) svm.train() Y_pred = svm.apply_binary(X_train) Y_train.get_labels() == Y_pred.get_labels() print "accuracy:", mean(Y_train.get_labels() == Y_pred.get_labels())
#!/usr/bin/python
from modshogun import CSVFile, RealFeatures, RescaleFeatures
from scipy.linalg import solve_triangular, cholesky, sqrtm, inv
import matplotlib.pyplot as pyplot
import numpy
# load wine features
features = RealFeatures(CSVFile('../data/fm_wine.dat'))
print('%d vectors with %d features.' % (features.get_num_vectors(), features.get_num_features()))
print('original features mean = ' + str(numpy.mean(features, axis=1)))
# rescale the features to [0,1]
feature_rescaling = RescaleFeatures()
feature_rescaling.init(features)
features.add_preprocessor(feature_rescaling)
features.apply_preprocessor()
print('mean after rescaling = ' + str(numpy.mean(features, axis=1)))
# remove mean from data
data = features.get_feature_matrix()
data = data.T
data-= numpy.mean(data, axis=0)
print numpy.mean(data, axis=0)
fig, axarr = pyplot.subplots(1,2)
axarr[0].matshow(numpy.cov(data.T))
#### whiten data
def serialization_complex_example (num=5, dist=1, dim=10, C=2.0, width=10):
import os
from numpy import concatenate, zeros, ones
from numpy.random import randn, seed
from modshogun import RealFeatures, MulticlassLabels
from modshogun import GMNPSVM
from modshogun import GaussianKernel
try:
from modshogun import SerializableHdf5File,SerializableAsciiFile, \
SerializableJsonFile,SerializableXmlFile,MSG_DEBUG
except ImportError:
return
from modshogun import NormOne, LogPlusOne
seed(17)
data=concatenate((randn(dim, num), randn(dim, num) + dist,
randn(dim, num) + 2*dist,
randn(dim, num) + 3*dist), axis=1)
lab=concatenate((zeros(num), ones(num), 2*ones(num), 3*ones(num)))
feats=RealFeatures(data)
#feats.io.set_loglevel(MSG_DEBUG)
#feats.io.enable_file_and_line()
kernel=GaussianKernel(feats, feats, width)
labels=MulticlassLabels(lab)
svm = GMNPSVM(C, kernel, labels)
feats.add_preprocessor(NormOne())
feats.add_preprocessor(LogPlusOne())
feats.set_preprocessed(1)
svm.train(feats)
bias_ref = svm.get_svm(0).get_bias()
#svm.print_serializable()
fstream = SerializableHdf5File("blaah.h5", "w")
status = svm.save_serializable(fstream)
check_status(status,'h5')
fstream = SerializableAsciiFile("blaah.asc", "w")
status = svm.save_serializable(fstream)
check_status(status,'asc')
fstream = SerializableJsonFile("blaah.json", "w")
status = svm.save_serializable(fstream)
check_status(status,'json')
fstream = SerializableXmlFile("blaah.xml", "w")
status = svm.save_serializable(fstream)
check_status(status,'xml')
fstream = SerializableHdf5File("blaah.h5", "r")
new_svm=GMNPSVM()
status = new_svm.load_serializable(fstream)
check_status(status,'h5')
new_svm.train()
bias_h5 = new_svm.get_svm(0).get_bias()
fstream = SerializableAsciiFile("blaah.asc", "r")
new_svm=GMNPSVM()
status = new_svm.load_serializable(fstream)
check_status(status,'asc')
new_svm.train()
bias_asc = new_svm.get_svm(0).get_bias()
fstream = SerializableJsonFile("blaah.json", "r")
new_svm=GMNPSVM()
status = new_svm.load_serializable(fstream)
check_status(status,'json')
new_svm.train()
bias_json = new_svm.get_svm(0).get_bias()
fstream = SerializableXmlFile("blaah.xml", "r")
new_svm=GMNPSVM()
status = new_svm.load_serializable(fstream)
check_status(status,'xml')
new_svm.train()
bias_xml = new_svm.get_svm(0).get_bias()
os.unlink("blaah.h5")
os.unlink("blaah.asc")
os.unlink("blaah.json")
os.unlink("blaah.xml")
return svm,new_svm, bias_ref, bias_h5, bias_asc, bias_json, bias_xml
def hsic_graphical():
# parameters, change to get different results
m=250
difference=3
# setting the angle lower makes a harder test
angle=pi/30
# number of samples taken from null and alternative distribution
num_null_samples=500
# use data generator class to produce example data
data=DataGenerator.generate_sym_mix_gauss(m,difference,angle)
# create shogun feature representation
features_x=RealFeatures(array([data[0]]))
features_y=RealFeatures(array([data[1]]))
# compute median data distance in order to use for Gaussian kernel width
# 0.5*median_distance normally (factor two in Gaussian kernel)
# However, shoguns kernel width is different to usual parametrization
# Therefore 0.5*2*median_distance^2
# Use a subset of data for that, only 200 elements. Median is stable
subset=int32(array([x for x in range(features_x.get_num_vectors())])) # numpy
subset=random.permutation(subset) # numpy permutation
subset=subset[0:200]
features_x.add_subset(subset)
dist=EuclideanDistance(features_x, features_x)
distances=dist.get_distance_matrix()
features_x.remove_subset()
median_distance=np.median(distances)
sigma_x=median_distance**2
features_y.add_subset(subset)
dist=EuclideanDistance(features_y, features_y)
distances=dist.get_distance_matrix()
features_y.remove_subset()
median_distance=np.median(distances)
sigma_y=median_distance**2
print "median distance for Gaussian kernel on x:", sigma_x
print "median distance for Gaussian kernel on y:", sigma_y
kernel_x=GaussianKernel(10,sigma_x)
kernel_y=GaussianKernel(10,sigma_y)
# create hsic instance. Note that this is a convienience constructor which copies
# feature data. features_x and features_y are not these used in hsic.
# This is only for user-friendlyness. Usually, its ok to do this.
# Below, the alternative distribution is sampled, which means
# that new feature objects have to be created in each iteration (slow)
# However, normally, the alternative distribution is not sampled
hsic=HSIC(kernel_x,kernel_y,features_x,features_y)
# sample alternative distribution
alt_samples=zeros(num_null_samples)
for i in range(len(alt_samples)):
data=DataGenerator.generate_sym_mix_gauss(m,difference,angle)
features_x.set_feature_matrix(array([data[0]]))
features_y.set_feature_matrix(array([data[1]]))
# re-create hsic instance everytime since feature objects are copied due to
# useage of convienience constructor
hsic=HSIC(kernel_x,kernel_y,features_x,features_y)
alt_samples[i]=hsic.compute_statistic()
# sample from null distribution
# permutation, biased statistic
hsic.set_null_approximation_method(PERMUTATION)
hsic.set_num_null_samples(num_null_samples)
null_samples_boot=hsic.sample_null()
# fit gamma distribution, biased statistic
hsic.set_null_approximation_method(HSIC_GAMMA)
gamma_params=hsic.fit_null_gamma()
# sample gamma with parameters
null_samples_gamma=array([gamma(gamma_params[0], gamma_params[1]) for _ in range(num_null_samples)])
# plot
figure()
# plot data x and y
subplot(2,2,1)
gca().xaxis.set_major_locator( MaxNLocator(nbins = 4) ) # reduce number of x-ticks
gca().yaxis.set_major_locator( MaxNLocator(nbins = 4) ) # reduce number of x-ticks
grid(True)
plot(data[0], data[1], 'o')
title('Data, rotation=$\pi$/'+str(1/angle*pi)+'\nm='+str(m))
xlabel('$x$')
ylabel('$y$')
# compute threshold for test level
alpha=0.05
null_samples_boot.sort()
null_samples_gamma.sort()
thresh_boot=null_samples_boot[floor(len(null_samples_boot)*(1-alpha))];
thresh_gamma=null_samples_gamma[floor(len(null_samples_gamma)*(1-alpha))];
type_one_error_boot=sum(null_samples_boot<thresh_boot)/float(num_null_samples)
type_one_error_gamma=sum(null_samples_gamma<thresh_boot)/float(num_null_samples)
# plot alternative distribution with threshold
subplot(2,2,2)
gca().xaxis.set_major_locator( MaxNLocator(nbins = 3) ) # reduce number of x-ticks
gca().yaxis.set_major_locator( MaxNLocator(nbins = 3) ) # reduce number of x-ticks
grid(True)
hist(alt_samples, 20, normed=True);
axvline(thresh_boot, 0, 1, linewidth=2, color='red')
type_two_error=sum(alt_samples<thresh_boot)/float(num_null_samples)
title('Alternative Dist.\n' + 'Type II error is ' + str(type_two_error))
# compute range for all null distribution histograms
hist_range=[min([min(null_samples_boot), min(null_samples_gamma)]), max([max(null_samples_boot), max(null_samples_gamma)])]
# plot null distribution with threshold
subplot(2,2,3)
gca().xaxis.set_major_locator( MaxNLocator(nbins = 3) ) # reduce number of x-ticks
gca().yaxis.set_major_locator( MaxNLocator(nbins = 3) ) # reduce number of x-ticks
grid(True)
hist(null_samples_boot, 20, range=hist_range, normed=True);
axvline(thresh_boot, 0, 1, linewidth=2, color='red')
title('Sampled Null Dist.\n' + 'Type I error is ' + str(type_one_error_boot))
# plot null distribution gamma
subplot(2,2,4)
gca().xaxis.set_major_locator( MaxNLocator(nbins = 3) ) # reduce number of x-ticks
gca().yaxis.set_major_locator( MaxNLocator(nbins = 3) ) # reduce number of x-ticks
grid(True)
hist(null_samples_gamma, 20, range=hist_range, normed=True);
axvline(thresh_gamma, 0, 1, linewidth=2, color='red')
title('Null Dist. Gamma\nType I error is ' + str(type_one_error_gamma))
grid(True)
# pull plots a bit apart
subplots_adjust(hspace=0.5)
subplots_adjust(wspace=0.5)
