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]
#!/usr/bin/env python
from tools.load import LoadMatrix
lm = LoadMatrix()
train_dna = lm.load_dna("../data/fm_train_dna.dat")
test_dna = lm.load_dna("../data/fm_test_dna.dat")
label = lm.load_labels("../data/label_train_dna.dat")
parameter_list = [[train_dna, test_dna, label, 20, 0.9, 1e-3, 1], [train_dna, test_dna, label, 20, 2.3, 1e-5, 4]]
def classifier_svmlight_batch_linadd_modular(
fm_train_dna, fm_test_dna, label_train_dna, degree, C, epsilon, num_threads
):
from modshogun import StringCharFeatures, BinaryLabels, DNA
from modshogun import WeightedDegreeStringKernel, MSG_DEBUG
try:
from modshogun 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
#!/usr/bin/env python
from tools.load import LoadMatrix
from numpy import random
lm=LoadMatrix()
random.seed(17)
ground_truth = lm.load_labels('../data/label_train_multiclass.dat')
predicted = lm.load_labels('../data/label_train_multiclass.dat') * 2
parameter_list = [[ground_truth,predicted]]
def evaluation_multiclassaccuracy_modular (ground_truth, predicted):
from shogun.Features import MulticlassLabels
from shogun.Evaluation import MulticlassAccuracy
ground_truth_labels = MulticlassLabels(ground_truth)
predicted_labels = MulticlassLabels(predicted)
evaluator = MulticlassAccuracy()
accuracy = evaluator.evaluate(predicted_labels,ground_truth_labels)
return accuracy
if __name__=='__main__':
print('MulticlassAccuracy')
evaluation_multiclassaccuracy_modular(*parameter_list[0])
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()
realfeat = RealFeatures(fm_train_real)
feats_train = SparseRealFeatures()
feats_train.obtain_from_simple(realfeat)
realfeat = RealFeatures(fm_test_real)
feats_test = SparseRealFeatures()
feats_test.obtain_from_simple(realfeat)
C = 0.9
epsilon = 1e-5
num_threads = 1
labels = Labels(label_train_twoclass)
svm = SVMOcas(C, feats_train, labels)
svm.set_epsilon(epsilon)
svm.parallel.set_num_threads(num_threads)
svm.set_bias_enabled(False)
svm.train()
svm.set_features(feats_test)
svm.classify().get_labels()
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")
label_train_twoclass = lm.load_labels("../data/label_train_twoclass.dat")
svmocas()
# the precision parameter epsilon=1e-5.
#
# For more details on the SVM^light see
# T. Joachims. Making large-scale SVM learning practical. In Advances in Kernel
# Methods -- Support Vector Learning, pages 169-184. MIT Press, Cambridge, MA USA, 1999.
#
# For more details on the Weighted Degree kernel see
# G. Raetsch, S.Sonnenburg, and B. Schoelkopf. RASE: recognition of alternatively
# spliced exons in C. elegans. Bioinformatics, 21:369-377, June 2005.
from tools.load import LoadMatrix
lm=LoadMatrix()
traindat = lm.load_dna('../data/fm_train_dna.dat')
testdat = lm.load_dna('../data/fm_test_dna.dat')
label_traindat = lm.load_labels('../data/label_train_dna.dat')
parameter_list = [[traindat,testdat,label_traindat,1.1,1e-5,1],[traindat,testdat,label_traindat,1.2,1e-5,1]]
def classifier_svmlight_modular (fm_train_dna=traindat,fm_test_dna=testdat,label_train_dna=label_traindat,C=1.2,epsilon=1e-5,num_threads=1):
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)
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,10,2.1,1.2,1e-5,False],
[traindat,testdat,train_label,10,2.1,1.3,1e-4,False]]
def classifier_libsvm (fm_train_real=traindat,fm_test_real=testdat,
label_train_twoclass=train_label,
size_cache=10, width=2.1,C=1.2,
epsilon=1e-5,use_bias=False):
sg('set_features', 'TRAIN', fm_train_real)
sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width)
sg('set_labels', 'TRAIN', label_train_twoclass)
sg('new_classifier', 'LIBSVM')
sg('svm_epsilon', epsilon)
sg('c', C)
sg('svm_use_bias', use_bias)
sg('train_classifier')
sg('set_features', 'TEST', fm_test_real)
result=sg('classify')
kernel_matrix = sg('get_kernel_matrix', 'TEST')
return result, kernel_matrix
if __name__=='__main__':
print('LibSVM')
# This example shows how to compute the Hamming Word Distance for string features.
from tools.load import LoadMatrix
lm=LoadMatrix()
traindna = lm.load_dna('../data/fm_train_dna.dat')
testdna = lm.load_dna('../data/fm_test_dna.dat')
testdat = lm.load_labels('../data/fm_test_real.dat')
parameter_list = [[traindna,testdna,testdat,4,0,False,False],
[traindna,testdna,testdat,3,0,False,False]]
def distance_hammingword_modular (fm_train_dna=traindna,fm_test_dna=testdna,
fm_test_real=testdat,order=3,gap=0,reverse=False,use_sign=False):
from shogun.Features import StringCharFeatures, StringWordFeatures, DNA
from shogun.Preprocessor import SortWordString
from shogun.Distance import HammingWordDistance
charfeat=StringCharFeatures(DNA)
charfeat.set_features(fm_train_dna)
feats_train=StringWordFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
preproc=SortWordString()
preproc.init(feats_train)
feats_train.add_preprocessor(preproc)
feats_train.apply_preprocessor()
charfeat=StringCharFeatures(DNA)
charfeat.set_features(fm_test_dna)
feats_test=StringWordFeatures(charfeat.get_alphabet())
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_multiclass.dat")
parameter_list = [[traindat, testdat, train_label, 3], [traindat, testdat, train_label, 4]]
def classifier_knn(fm_train_real=traindat, fm_test_real=testdat, label_train_multiclass=train_label, k=3):
sg("set_features", "TRAIN", fm_train_real)
sg("set_labels", "TRAIN", label_train_multiclass)
sg("set_distance", "EUCLIDIAN", "REAL")
sg("new_classifier", "KNN")
sg("train_classifier", k)
sg("set_features", "TEST", fm_test_real)
result = sg("classify")
return result
if __name__ == "__main__":
print("KNN")
classifier_knn(*parameter_list[0])
from tools.load import LoadMatrix
lm = LoadMatrix()
traindat = lm.load_dna('../data/fm_train_dna.dat')
testdat = lm.load_dna('../data/fm_test_dna.dat')
label_traindat = lm.load_labels('../data/label_train_dna.dat')
parameter_list = [[traindat, testdat, label_traindat, 3, 0, False],
[traindat, testdat, label_traindat, 3, 0, False]]
def kernel_histogram_word_string_modular(fm_train_dna=traindat,
fm_test_dna=testdat,
label_train_dna=label_traindat,
order=3,
gap=0,
reverse=False):
from shogun.Features import StringCharFeatures, StringWordFeatures, DNA, Labels
from shogun.Kernel import HistogramWordStringKernel
from shogun.Classifier import PluginEstimate #, MSG_DEBUG
reverse = reverse
charfeat = StringCharFeatures(DNA)
#charfeat.io.set_loglevel(MSG_DEBUG)
charfeat.set_features(fm_train_dna)
feats_train = StringWordFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_test_dna)
feats_test = StringWordFeatures(charfeat.get_alphabet())
#!/usr/bin/env python
from tools.load import LoadMatrix
lm=LoadMatrix()
traindna = lm.load_dna('../data/fm_train_dna.dat')
testdna = lm.load_dna('../data/fm_test_dna.dat')
testdat = lm.load_labels('../data/fm_test_real.dat')
parameter_list = [[traindna,testdna,testdat,4,0,False,False],
[traindna,testdna,testdat,3,0,False,False]]
def distance_hammingword (fm_train_dna=traindna,fm_test_dna=testdna,
fm_test_real=testdat,order=3,gap=0,reverse=False,use_sign=False):
from shogun import StringCharFeatures, StringWordFeatures, DNA
from shogun import SortWordString
from shogun import HammingWordDistance
charfeat=StringCharFeatures(DNA)
charfeat.set_features(fm_train_dna)
feats_train=StringWordFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
preproc=SortWordString()
preproc.init(feats_train)
feats_train.add_preprocessor(preproc)
feats_train.apply_preprocessor()
charfeat=StringCharFeatures(DNA)
charfeat.set_features(fm_test_dna)
feats_test=StringWordFeatures(charfeat.get_alphabet())
feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse)
# In this example PRC (Precision-Recall curve) is being computed
# for the pair of ground truth toy labels and random labels.
# PRC curve (as matrix) and auPRC (area under PRC) is returned.
from tools.load import LoadMatrix
from numpy import random
lm = LoadMatrix()
ground_truth = lm.load_labels('../data/label_train_twoclass.dat')
random.seed(17)
predicted = random.randn(len(ground_truth))
parameter_list = [[ground_truth, predicted]]
def evaluation_prcevaluation_modular(ground_truth, predicted):
from shogun.Features import BinaryLabels
from shogun.Evaluation import PRCEvaluation
ground_truth_labels = BinaryLabels(ground_truth)
predicted_labels = BinaryLabels(predicted)
evaluator = PRCEvaluation()
evaluator.evaluate(predicted_labels, ground_truth_labels)
return evaluator.get_PRC(), evaluator.get_auPRC()
if __name__ == '__main__':
print('PRCEvaluation')
evaluation_prcevaluation_modular(*parameter_list[0])
# In this example a multiclass accuracy is being computed for toy data labels
# and toy data labels multiplied by two.
from tools.load import LoadMatrix
from numpy import random
lm = LoadMatrix()
random.seed(17)
ground_truth = lm.load_labels('../data/label_train_multiclass.dat')
predicted = lm.load_labels('../data/label_train_multiclass.dat') * 2
parameter_list = [[ground_truth, predicted]]
def evaluation_multiclassaccuracy_modular(ground_truth, predicted):
from shogun.Features import Labels
from shogun.Evaluation import MulticlassAccuracy
ground_truth_labels = Labels(ground_truth)
predicted_labels = Labels(predicted)
evaluator = MulticlassAccuracy()
accuracy = evaluator.evaluate(predicted_labels, ground_truth_labels)
return accuracy
if __name__ == '__main__':
print 'MulticlassAccuracy'
evaluation_multiclassaccuracy_modular(*parameter_list[0])
#!/usr/bin/env python
"""
Explicit examples on how to use the different classifiers
"""
from numpy import double, array, floor, concatenate, sign, ones, zeros, char, int
from numpy.random import rand, seed, permutation
from sg import sg
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')
fm_train_dna=lm.load_dna('../data/fm_train_dna.dat')
fm_test_dna=lm.load_dna('../data/fm_test_dna.dat')
label_train_dna=lm.load_labels('../data/label_train_dna.dat')
label_train_twoclass=lm.load_labels('../data/label_train_twoclass.dat')
label_train_multiclass=lm.load_labels('../data/label_train_multiclass.dat')
###########################################################################
# kernel-based SVMs
###########################################################################
def svm_light ():
print 'SVMLight'
size_cache=10
degree=20
C=0.017
epsilon=1e-5
use_bias=False
# The base kernels are then subsequently added to a CombinedKernel, which
# contains a weight for each kernel and encapsulates the base kernels
# from the training procedure. When the CombinedKernel between two examples is
# evaluated it computes the corresponding linear combination of kernels according to their weights.
# We then show how to create an MKLMultiClass classifier that trains an SVM and learns the optimal
# weighting of kernels (w.r.t. a given norm q) at the same time. The main difference to the binary
# classification version of MKL is that we can use more than two values as labels, when training
# the classifier.
# Finally, the example shows how to classify with a trained MKLMultiClass classifier.
#
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()
from tools.load import LoadMatrix
from numpy import random
lm=LoadMatrix()
ground_truth = lm.load_labels('../data/label_train_twoclass.dat')
random.seed(17)
predicted = random.randn(len(ground_truth))
parameter_list = [[ground_truth,predicted]]
def evaluation_prcevaluation_modular(ground_truth, predicted):
from shogun.Features import Labels
from shogun.Evaluation import PRCEvaluation
ground_truth_labels = Labels(ground_truth)
predicted_labels = Labels(predicted)
evaluator = PRCEvaluation()
evaluator.evaluate(predicted_labels,ground_truth_labels)
return evaluator.get_PRC(), evaluator.get_auPRC()
if __name__=='__main__':
print 'PRCEvaluation'
evaluation_prcevaluation_modular(*parameter_list[0])
from tools.load import LoadMatrix
lm = LoadMatrix()
traindna = lm.load_dna("../data/fm_train_dna.dat")
testdna = lm.load_dna("../data/fm_test_dna.dat")
testdat = lm.load_labels("../data/fm_test_real.dat")
parameter_list = [[traindna, testdna, testdat, 4, 0, False, False], [traindna, testdna, testdat, 3, 0, False, False]]
def distance_hammingword_modular(
fm_train_dna=traindna, fm_test_dna=testdna, fm_test_real=testdat, order=3, gap=0, reverse=False, use_sign=False
):
from shogun.Features import StringCharFeatures, StringWordFeatures, DNA
from shogun.Preprocessor import SortWordString
from shogun.Distance import HammingWordDistance
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_train_dna)
feats_train = StringWordFeatures(charfeat.get_alphabet())
feats_train.obtain_from_char(charfeat, order - 1, order, gap, reverse)
preproc = SortWordString()
preproc.init(feats_train)
feats_train.add_preproc(preproc)
feats_train.apply_preproc()
charfeat = StringCharFeatures(DNA)
charfeat.set_features(fm_test_dna)
feats_test = StringWordFeatures(charfeat.get_alphabet())
from tools.load import LoadMatrix
lm=LoadMatrix()
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')
parameter_list = [[traindat,testdat,label_traindat,0.9,1,2000],[traindat,testdat,label_traindat,3,1,5000]]
def classifier_larank_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_multiclass=label_traindat,C=0.9,num_threads=1,num_iter=5):
from shogun.Features import RealFeatures, Labels
from shogun.Kernel import GaussianKernel
from shogun.Classifier import LaRank
from shogun.Mathematics import Math_init_random
Math_init_random(17)
feats_train=RealFeatures(fm_train_real)
feats_test=RealFeatures(fm_test_real)
width=2.1
kernel=GaussianKernel(feats_train, feats_train, width)
epsilon=1e-5
labels=Labels(label_train_multiclass)
svm=LaRank(C, kernel, labels)
#svm.set_tau(1e-3)
svm.set_batch_mode(False)
#svm.io.enable_progress()
svm.set_epsilon(epsilon)
svm.train()
out=svm.apply(feats_train).get_labels()
# In this example a support vector regression algorithm is trained on a
# real-valued toy data set. The underlying library used for the SVR training is
# LIBSVM. The SVR is trained with regularization parameter C=1 and a gaussian
# kernel with width=2.1.
#
# For more details on LIBSVM solver see http://www.csie.ntu.edu.tw/~cjlin/libsvm/ .
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')
trainlabel=lm.load_labels('../data/label_train_regression.dat')
parameter_list=[[traindat,testdat,trainlabel,10,2.1,1.2,1e-5,1e-2],
[traindat,testdat,trainlabel,11,2.3,1.3,1e-6,1e-3]]
def regression_libsvr (fm_train=traindat,fm_test=testdat,
label_train=trainlabel,size_cache=10,width=2.1,
C=1.2,epsilon=1e-5,tube_epsilon=1e-2):
sg('set_features', 'TRAIN', fm_train)
sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width)
sg('set_labels', 'TRAIN', label_train)
sg('new_regression', 'LIBSVR')
sg('svr_tube_epsilon', tube_epsilon)
sg('c', C)
sg('train_regression')
sg('set_features', 'TEST', fm_test)
# In this example a two-class linear support vector machine classifier is trained
# on a toy data set and the trained classifier is used to predict labels of test
# examples. As training algorithm the Stochastic Gradient Descent (SGD) solver is
# used with the SVM regularization parameter C=0.9. The number of iterations, i.e.
# passes though all training examples, is set to num_iter=5 .
#
# For more details on the SGD solver see
# L. Bottou, O. Bousquet. The tradeoff of large scale learning. In NIPS 20. MIT
# Press. 2008.
from tools.load import LoadMatrix
lm=LoadMatrix()
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_twoclass.dat')
parameter_list = [[traindat,testdat,label_traindat,0.9,1,6],[traindat,testdat,label_traindat,0.8,1,5]]
def classifier_svmsgd_modular (fm_train_real=traindat,fm_test_real=testdat,label_train_twoclass=label_traindat,C=0.9,num_threads=1,num_iter=5):
from shogun.Features import RealFeatures, SparseRealFeatures, Labels
from shogun.Classifier import SVMSGD
realfeat=RealFeatures(fm_train_real)
feats_train=SparseRealFeatures()
feats_train.obtain_from_simple(realfeat)
realfeat=RealFeatures(fm_test_real)
feats_test=SparseRealFeatures()
feats_test.obtain_from_simple(realfeat)
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')
trainlabel = lm.load_labels('../data/label_train_regression.dat')
parameter_list = [[traindat, testdat, trainlabel, 10, 2.1, 1.2, 1e-5, 1e-2],
[traindat, testdat, trainlabel, 11, 2.3, 1.3, 1e-6, 1e-3]]
def regression_libsvr(fm_train=traindat,
fm_test=testdat,
label_train=trainlabel,
size_cache=10,
width=2.1,
C=1.2,
epsilon=1e-5,
tube_epsilon=1e-2):
sg('set_features', 'TRAIN', fm_train)
sg('set_kernel', 'GAUSSIAN', 'REAL', size_cache, width)
sg('set_labels', 'TRAIN', label_train)
sg('new_regression', 'LIBSVR')
sg('svr_tube_epsilon', tube_epsilon)
sg('c', C)
sg('train_regression')
sg('set_features', 'TEST', fm_test)
result = sg('classify')