def prepare_data(use_toy=True):
from os.path import exists
from tools.load import LoadMatrix
lm=LoadMatrix()
if not use_toy and exists('../data/../mldata/uci-20070111-optdigits.mat'):
from scipy.io import loadmat
mat = loadmat('../data/../mldata/uci-20070111-optdigits.mat')['int0'].astype(float)
X = mat[:-1,:]
Y = mat[-1,:]
isplit = X.shape[1]/2
traindat = X[:,:isplit]
label_traindat = Y[:isplit]
testdat = X[:, isplit:]
label_testdat = Y[isplit:]
else:
traindat = lm.load_numbers('../data/fm_train_real.dat')
testdat = lm.load_numbers('../data/fm_test_real.dat')
label_traindat = lm.load_labels('../data/label_train_multiclass.dat')
label_testdat = None
return [traindat, label_traindat, testdat, label_testdat]
# This is an example for the initialization of a linear kernel on word (2byte)
# data.
from tools.load import LoadMatrix
from numpy import ushort
lm = LoadMatrix()
traindat = ushort(lm.load_numbers("../data/fm_train_word.dat"))
testdat = ushort(lm.load_numbers("../data/fm_test_word.dat"))
parameter_list = [[traindat, testdat, 1.2], [traindat, testdat, 1.2]]
def kernel_linear_word_modular(fm_train_word=traindat, fm_test_word=testdat, scale=1.2):
from shogun.Kernel import LinearKernel, AvgDiagKernelNormalizer
from shogun.Features import WordFeatures
feats_train = WordFeatures(fm_train_word)
feats_test = WordFeatures(fm_test_word)
kernel = LinearKernel(feats_train, feats_train)
kernel.set_normalizer(AvgDiagKernelNormalizer(scale))
kernel.init(feats_train, feats_train)
km_train = kernel.get_kernel_matrix()
kernel.init(feats_train, feats_test)
km_test = kernel.get_kernel_matrix()
return kernel
def distance():
print "Distance"
width = 1.7
size_cache = 10
from sg import sg
sg("set_features", "TRAIN", fm_train_real)
sg("set_features", "TEST", fm_test_real)
sg("set_distance", "EUCLIDIAN", "REAL")
sg("set_kernel", "DISTANCE", size_cache, width)
km = sg("get_kernel_matrix", "TRAIN")
km = sg("get_kernel_matrix", "TEST")
if __name__ == "__main__":
from tools.load import LoadMatrix
lm = LoadMatrix()
fm_train_real = lm.load_numbers("../data/fm_train_real.dat")
fm_test_real = lm.load_numbers("../data/fm_test_real.dat")
distance()
epsilon=1e-5
labels=Labels(label_train_twoclass)
svm=LibSVM(C, kernel, labels)
svm.set_epsilon(epsilon)
svm.train()
#kernel.init(feats_train, feats_test)
output = svm.classify(feats_test)#.get_labels()
#output_vector = output.get_labels()
out=svm.classify().get_labels()
testerr=mean(sign(out)!=testlab)
print testerr
#sv_idx=svm.get_support_vectors()
#alphas=svm.get_alphas()
#pm = PerformanceMeasures(output_vector, output)
#acc = pm.get_accuracy()
#roc = pm.get_auROC()
#fms = pm.get_fmeasure()
if __name__=='__main__':
from tools.load import LoadMatrix
lm=LoadMatrix()
fm_train_real=lm.load_numbers('/home/mati/lib/shogun-0.9.3/examples/documented/data/fm_train_real.dat')
fm_test_real=lm.load_numbers('/home/mati/lib/shogun-0.9.3/examples/documented/data/fm_test_real.dat')
label_train_twoclass=lm.load_labels('/home/mati/lib/shogun-0.9.3/examples/documented/data/label_train_twoclass.dat')
libsvm()
def bray_curtis_distance ():
print 'BrayCurtisDistance'
from sg import sg
sg('set_distance', 'BRAYCURTIS', 'REAL')
sg('set_features', 'TRAIN', fm_train_real)
dm=sg('get_distance_matrix', 'TRAIN')
sg('set_features', 'TEST', fm_test_real)
dm=sg('get_distance_matrix', 'TEST')
if __name__=='__main__':
from tools.load import LoadMatrix
lm=LoadMatrix()
fm_train_real=lm.load_numbers('../data/fm_train_real.dat')
fm_test_real=lm.load_numbers('../data/fm_test_real.dat')
bray_curtis_distance()
from tools.load import LoadMatrix
lm=LoadMatrix()
data = lm.load_numbers('../data/fm_train_real.dat')
parameter_list = [[data, 0.01, 1.0], [data, 0.05, 2.0]]
def preprocessor_kernelpcacut_modular(data, threshold, width):
from shogun.Features import RealFeatures
from shogun.Preprocessor import KernelPCACut
from shogun.Kernel import GaussianKernel
features = RealFeatures(data)
kernel = GaussianKernel(features,features,width)
preprocessor = KernelPCACut(kernel,threshold)
preprocessor.init(features)
preprocessor.apply_to_feature_matrix(features)
return features
if __name__=='__main__':
print 'KernelPCACut'
preprocessor_kernelpcacut_modular(*parameter_list[0])
# (w(t),b(t)) are the current parameters of the linear classifier
# (w(t+1),b(t+1)) are the new parameters of the linear classifier
# alpha is the learning rate.
#
# The Perceptron algorithm iterates until all training examples are correctly
# classified or the prescribed maximal number of iterations is reached.
#
# The learning rate and the maximal number of iterations can be set by
# sg('set_perceptron_parameters', alpha, max_iter);
#
from tools.load import LoadMatrix
from sg import sg
lm = LoadMatrix()
traindat = lm.load_numbers('../data/fm_train_real.dat')
testdat = lm.load_numbers('../data/fm_test_real.dat')
train_label = lm.load_labels('../data/label_train_twoclass.dat')
parameter_list = [[traindat, testdat, train_label],
[traindat, testdat, train_label]]
def classifier_perceptron(fm_train_real=traindat,
fm_test_real=testdat,
label_train_twoclass=train_label):
sg('set_features', 'TRAIN', fm_train_real)
sg('set_labels', 'TRAIN', label_train_twoclass)
sg('new_classifier', 'PERCEPTRON')
# often does not converge, mind your data!
sg('train_classifier')
#!/usr/bin/env python
from tools.load import LoadMatrix
lm=LoadMatrix()
data=lm.load_numbers('../data/fm_train_real.dat')
label=lm.load_numbers('../data/label_train_twoclass.dat')
parameter_list=[[data,label]]
def features_io_modular (fm_train_real, label_train_twoclass):
import numpy
from modshogun import SparseRealFeatures, RealFeatures, MulticlassLabels
from modshogun import GaussianKernel
from modshogun import LibSVMFile, CSVFile, BinaryFile, HDF5File
feats=SparseRealFeatures(fm_train_real)
feats2=SparseRealFeatures()
f=BinaryFile("tmp/fm_train_sparsereal.bin","w")
feats.save(f)
f=LibSVMFile("tmp/fm_train_sparsereal.ascii","w")
feats.save(f)
f=BinaryFile("tmp/fm_train_sparsereal.bin")
feats2.load(f)
f=LibSVMFile("tmp/fm_train_sparsereal.ascii")
feats2.load(f)
feats=RealFeatures(fm_train_real)
feats2=RealFeatures()
#!/usr/bin/env python
from tools.load import LoadMatrix
lm = LoadMatrix()
fm_train_real = lm.load_numbers('../data/fm_train_real.dat')
fm_test_real = lm.load_numbers('../data/fm_test_real.dat')
label_train_multiclass = lm.load_labels('../data/label_train_multiclass.dat')
parameter_list = [[
fm_train_real, fm_test_real, label_train_multiclass, 1.2, 1.2, 1e-5, 1,
0.001, 1.5
],
[
fm_train_real, fm_test_real, label_train_multiclass, 5,
1.2, 1e-2, 1, 0.001, 2
]]
def mkl_multiclass_modular(fm_train_real, fm_test_real, label_train_multiclass,
width, C, epsilon, num_threads, mkl_epsilon,
mkl_norm):
from shogun.Features import CombinedFeatures, RealFeatures, MulticlassLabels
from shogun.Kernel import CombinedKernel, GaussianKernel, LinearKernel, PolyKernel
from shogun.Classifier import MKLMulticlass
kernel = CombinedKernel()
feats_train = CombinedFeatures()
feats_test = CombinedFeatures()
subkfeats_train = RealFeatures(fm_train_real)
subkfeats_test = RealFeatures(fm_test_real)
from tools.load import LoadMatrix
from numpy import ushort
lm=LoadMatrix()
traindat = ushort(lm.load_numbers('../data/fm_train_word.dat'))
testdat = ushort(lm.load_numbers('../data/fm_test_word.dat'))
parameter_list=[[traindat,testdat,1.2],[traindat,testdat,1.2]]
def kernel_linear_word_modular (fm_train_word=traindat,fm_test_word=testdat,scale=1.2):
from shogun.Kernel import LinearKernel, AvgDiagKernelNormalizer
from shogun.Features import WordFeatures
feats_train=WordFeatures(fm_train_word)
feats_test=WordFeatures(fm_test_word)
kernel=LinearKernel(feats_train, feats_train)
kernel.set_normalizer(AvgDiagKernelNormalizer(scale))
kernel.init(feats_train, feats_train)
km_train=kernel.get_kernel_matrix()
kernel.init(feats_train, feats_test)
km_test=kernel.get_kernel_matrix()
return kernel
if __name__=='__main__':
print 'LinearWord'
kernel_linear_word_modular(*parameter_list[0])
#!/usr/bin/env python
from tools.load import LoadMatrix
lm = LoadMatrix()
data = lm.load_numbers('../data/fm_train_real.dat')
label = lm.load_numbers('../data/label_train_twoclass.dat')
parameter_list = [[data, label]]
def features_io_modular(fm_train_real, label_train_twoclass):
import numpy
from modshogun import SparseRealFeatures, RealFeatures, MulticlassLabels
from modshogun import GaussianKernel
from modshogun import LibSVMFile, CSVFile, BinaryFile, HDF5File
feats = SparseRealFeatures(fm_train_real)
feats2 = SparseRealFeatures()
f = BinaryFile("tmp/fm_train_sparsereal.bin", "w")
feats.save(f)
f = LibSVMFile("tmp/fm_train_sparsereal.ascii", "w")
feats.save(f)
f = BinaryFile("tmp/fm_train_sparsereal.bin")
feats2.load(f)
f = LibSVMFile("tmp/fm_train_sparsereal.ascii")
feats2.load(f)
feats = RealFeatures(fm_train_real)
#!/usr/bin/env python
from tools.load import LoadMatrix
from modshogun import *
lm=LoadMatrix()
data = lm.load_numbers('../data/fm_train_real.dat')
labels = lm.load_numbers('../data/label_train_multiclass.dat')
parameter_list = [[data, labels, CANVAR_FLDA], [data, labels, CLASSIC_FLDA]]
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
if __name__=='__main__':
print('FisherLda')
preprocessor_fisherlda_modular(*parameter_list[0])
###########################################################################
# kernel can be used to maximize AUC instead of margin in SVMs
###########################################################################
from tools.load import LoadMatrix
from numpy import double
lm = LoadMatrix()
traindat = double(lm.load_numbers("../data/fm_train_real.dat"))
testdat = lm.load_labels("../data/label_train_twoclass.dat")
parameter_list = [[traindat, testdat, 1.7], [traindat, testdat, 1.6]]
def kernel_auc_modular(fm_train_real=traindat, label_train_real=testdat, width=1.7):
from shogun.Kernel import GaussianKernel, AUCKernel
from shogun.Features import RealFeatures, Labels
feats_train = RealFeatures(fm_train_real)
subkernel = GaussianKernel(feats_train, feats_train, width)
kernel = AUCKernel(0, subkernel)
kernel.setup_auc_maximization(Labels(label_train_real))
km_train = kernel.get_kernel_matrix()
return kernel
if __name__ == "__main__":
print "AUC"
kernel_auc_modular(*parameter_list[0])
###########################################################################
# linear kernel on byte features
###########################################################################
from tools.load import LoadMatrix
from numpy import ubyte
lm=LoadMatrix()
traindat = ubyte(lm.load_numbers('../data/fm_train_byte.dat'))
testdat = ubyte(lm.load_numbers('../data/fm_test_byte.dat'))
parameter_list=[[traindat,testdat],[traindat,testdat]]
def kernel_linear_byte_modular(fm_train_byte=traindat,fm_test_byte=testdat):
from shogun.Kernel import LinearKernel
from shogun.Features import ByteFeatures
feats_train=ByteFeatures(fm_train_byte)
feats_test=ByteFeatures(fm_test_byte)
kernel=LinearKernel(feats_train, feats_train)
km_train=kernel.get_kernel_matrix()
kernel.init(feats_train, feats_test)
km_test=kernel.get_kernel_matrix()
return kernel
if __name__=='__main__':
print('LinearByte')
kernel_linear_byte_modular(*parameter_list[0])
###########################################################################
# anova kernel
###########################################################################
from tools.load import LoadMatrix
from numpy import double
lm = LoadMatrix()
traindat = double(lm.load_numbers('../data/fm_train_real.dat'))
testdat = double(lm.load_numbers('../data/fm_test_real.dat'))
parameter_list = [[traindat, testdat, 2, 10], [traindat, testdat, 5, 10]]
def kernel_anova_modular(fm_train_real=traindat,
fm_test_real=testdat,
cardinality=2,
size_cache=10):
from shogun.Kernel import ANOVAKernel
from shogun.Features import RealFeatures
feats_train = RealFeatures(fm_train_real)
feats_test = RealFeatures(fm_test_real)
kernel = ANOVAKernel(feats_train, feats_train, cardinality, size_cache)
for i in range(0, feats_train.get_num_vectors()):
for j in range(0, feats_train.get_num_vectors()):
k1 = kernel.compute_rec1(i, j)
k2 = kernel.compute_rec2(i, j)
if abs(k1 - k2) > 1e-10:
print "|%s|%s|" % (k1, k2)
from tools.load import LoadMatrix
from numpy import ushort
from sg import sg
lm=LoadMatrix()
trainword=ushort(lm.load_numbers('../data/fm_test_word.dat'))
testword=ushort(lm.load_numbers('../data/fm_test_word.dat'))
parameter_list=[[trainword,testword,10,1.4],
[trainword,testword,11,1.5]]
def kernel_linearword (fm_train_word=trainword,fm_test_word=testword,
size_cache=10, scale=1.4):
sg('set_features', 'TRAIN', fm_train_word)
sg('set_features', 'TEST', fm_test_word)
sg('set_kernel', 'LINEAR', 'WORD', size_cache, scale)
km=sg('get_kernel_matrix', 'TRAIN')
km=sg('get_kernel_matrix', 'TEST')
return km
if __name__=='__main__':
print('LinearWord')
kernel_linearword(*parameter_list[0])
from tools.load import LoadMatrix
lm=LoadMatrix()
data = lm.load_numbers('../data/fm_train_real.dat')
parameter_list = [[data,10],[data,20]]
def converter_locallylinearembedding_modular(data,k):
from shogun.Features import RealFeatures
from shogun.Converter import LocallyLinearEmbedding
features = RealFeatures(data)
converter = LocallyLinearEmbedding()
converter.set_target_dim(1)
converter.set_k(k)
converter.apply(features)
return features
if __name__=='__main__':
print 'LocallyLinearEmbedding'
converter_locallylinearembedding_modular(*parameter_list[0])
###########################################################################
# anova kernel
###########################################################################
from tools.load import LoadMatrix
from numpy import double
lm=LoadMatrix()
traindat = double(lm.load_numbers('../data/fm_train_real.dat'))
testdat = double(lm.load_numbers('../data/fm_test_real.dat'))
parameter_list = [[traindat,testdat,2,10], [traindat,testdat,5,10]]
def kernel_anova_modular (fm_train_real=traindat,fm_test_real=testdat,cardinality=2, size_cache=10):
from shogun.Kernel import ANOVAKernel
from shogun.Features import RealFeatures
feats_train=RealFeatures(fm_train_real)
feats_test=RealFeatures(fm_test_real)
kernel=ANOVAKernel(feats_train, feats_train, cardinality, size_cache)
for i in range(0,feats_train.get_num_vectors()):
for j in range(0,feats_train.get_num_vectors()):
k1 = kernel.compute_rec1(i,j)
k2 = kernel.compute_rec2(i,j)
#if abs(k1-k2) > 1e-10:
# print "|%s|%s|" % (k1, k2)
km_train=kernel.get_kernel_matrix()
kernel.init(feats_train, feats_test)
km_test=kernel.get_kernel_matrix()
return km_train, km_test, kernel
#!/usr/bin/env python
from tools.load import LoadMatrix
from modshogun import *
lm=LoadMatrix()
data = lm.load_numbers('../data/fm_train_real.dat')
labels = lm.load_numbers('../data/label_train_multiclass.dat')
parameter_list = [[data, labels, CANVAR_FLDA], [data, labels, CLASSIC_FLDA]]
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.fit(sg_features, sg_labels, 1)
yn=preprocessor.apply_to_feature_matrix(sg_features)
return yn
if __name__=='__main__':
print('FisherLda')
preprocessor_fisherlda_modular(*parameter_list[0])
from tools.load import LoadMatrix
import numpy
lm = LoadMatrix()
data = lm.load_numbers("../data/fm_train_real.dat")
parameter_list = [[data]]
def converter_multidimensionalscaling_modular(data):
from shogun.Features import RealFeatures
from shogun.Converter import MultidimensionalScaling
from shogun.Distance import EuclidianDistance
features = RealFeatures(data)
distance_before = EuclidianDistance()
distance_before.init(features, features)
converter = MultidimensionalScaling()
converter.set_target_dim(2)
converter.set_landmark(False)
embedding = converter.apply(features)
distance_after = EuclidianDistance()
distance_after.init(embedding, embedding)
distance_matrix_after = distance_after.get_distance_matrix()
distance_matrix_before = distance_before.get_distance_matrix()
return numpy.linalg.norm(distance_matrix_after - distance_matrix_before) / numpy.linalg.norm(distance_matrix_before)
from tools.load import LoadMatrix
from sg import sg
lm = LoadMatrix()
trainbyte = ubyte(lm.load_numbers("../data/fm_train_byte.dat"))
testbyte = ubyte(lm.load_numbers("../data/fm_test_byte.dat"))
parameter_list = [[trainbyte, testbyte], [trainbyte, testbyte]]
def kernel_linearbyte(fm_train_byte=trainbyte, fm_test_byte=testbyte):
# import pdb
# pdb.set_trace()
sg("set_features", "TRAIN", fm_train_byte)
sg("set_features", "TEST", fm_test_byte, "RAWBYTE")
sg("set_kernel", "LINEAR", "BYTE", 10)
km = sg("get_kernel_matrix", "TRAIN")
km = sg("get_kernel_matrix", "TEST")
return km
if __name__ == "__main__":
print "LinearByte"
kernel_linearbyte(*parameter_list[0])
from tools.load import LoadMatrix
from sg import sg
lm=LoadMatrix()
traindat=lm.load_numbers('../data/fm_train_real.dat')
testdat=lm.load_numbers('../data/fm_test_real.dat')
parameter_list=[[traindat,testdat,1.4,10,True],[traindat,testdat,1.5,11,True]]
def preproc_prunevarsubmean (fm_train_real=traindat,fm_test_real=testdat,
width=1.4,size_cache=10,divide_by_std=True):
sg('add_preproc', 'PRUNEVARSUBMEAN', divide_by_std)
sg('set_kernel', 'CHI2', 'REAL', size_cache, width)
sg('set_features', 'TRAIN', fm_train_real)
sg('attach_preproc', 'TRAIN')
km=sg('get_kernel_matrix', 'TRAIN')
sg('set_features', 'TEST', fm_test_real)
sg('attach_preproc', 'TEST')
km=sg('get_kernel_matrix', 'TEST')
return km
if __name__=='__main__':
print 'PruneVarSubMean'
preproc_prunevarsubmean(*parameter_list[0])
###########################################################################
# linear kernel on byte features
###########################################################################
from tools.load import LoadMatrix
from numpy import ubyte
lm = LoadMatrix()
traindat = ubyte(lm.load_numbers('../data/fm_train_byte.dat'))
testdat = ubyte(lm.load_numbers('../data/fm_test_byte.dat'))
parameter_list = [[traindat, testdat], [traindat, testdat]]
def kernel_linear_byte_modular(fm_train_byte=traindat, fm_test_byte=testdat):
from shogun.Kernel import LinearKernel
from shogun.Features import ByteFeatures
feats_train = ByteFeatures(fm_train_byte)
feats_test = ByteFeatures(fm_test_byte)
kernel = LinearKernel(feats_train, feats_train)
km_train = kernel.get_kernel_matrix()
kernel.init(feats_train, feats_test)
km_test = kernel.get_kernel_matrix()
return kernel
if __name__ == '__main__':
print 'LinearByte'
kernel_linear_byte_modular(*parameter_list[0])