def kernel_combined_custom_poly_modular(train_fname=traindat,
test_fname=testdat,
train_label_fname=label_traindat):
from modshogun import CombinedFeatures, RealFeatures, BinaryLabels
from modshogun import CombinedKernel, PolyKernel, CustomKernel
from modshogun import LibSVM, CSVFile
kernel = CombinedKernel()
feats_train = CombinedFeatures()
tfeats = RealFeatures(CSVFile(train_fname))
tkernel = PolyKernel(10, 3)
tkernel.init(tfeats, tfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_train = RealFeatures(CSVFile(train_fname))
feats_train.append_feature_obj(subkfeats_train)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_train)
labels = BinaryLabels(CSVFile(train_label_fname))
svm = LibSVM(1.0, kernel, labels)
svm.train()
kernel = CombinedKernel()
feats_pred = CombinedFeatures()
pfeats = RealFeatures(CSVFile(test_fname))
tkernel = PolyKernel(10, 3)
tkernel.init(tfeats, pfeats)
K = tkernel.get_kernel_matrix()
kernel.append_kernel(CustomKernel(K))
subkfeats_test = RealFeatures(CSVFile(test_fname))
feats_pred.append_feature_obj(subkfeats_test)
subkernel = PolyKernel(10, 2)
kernel.append_kernel(subkernel)
kernel.init(feats_train, feats_pred)
svm.set_kernel(kernel)
svm.apply()
km_train = kernel.get_kernel_matrix()
return km_train, kernel
def word_kernel(words):
N = len(words)
dist_matrix = np.zeros([N, N])
for i in xrange(N):
for j in xrange(i, N):
s = difflib.SequenceMatcher(None, words[i], words[j])
dist_matrix[i, j] = s.ratio()
dist_matrix = 0.5 * (dist_matrix + dist_matrix.T)
return CustomKernel(dist_matrix)
def classifier_custom_kernel_modular(C=1, dim=7):
from modshogun import RealFeatures, BinaryLabels, CustomKernel, LibSVM
from numpy import diag, ones, sign
from numpy.random import rand, seed
seed((C, dim))
lab = sign(2 * rand(dim) - 1)
data = rand(dim, dim)
symdata = data * data.T + diag(ones(dim))
kernel = CustomKernel()
kernel.set_full_kernel_matrix_from_full(data)
labels = BinaryLabels(lab)
svm = LibSVM(C, kernel, labels)
svm.train()
predictions = svm.apply()
out = svm.apply().get_labels()
return svm, out
def classifier_custom_kernel_modular (C=1,dim=7):
from modshogun import RealFeatures, BinaryLabels, CustomKernel, LibSVM
from numpy import diag,ones,sign
from numpy.random import rand,seed
seed((C,dim))
lab=sign(2*rand(dim) - 1)
data=rand(dim, dim)
symdata=data*data.T + diag(ones(dim))
kernel=CustomKernel()
kernel.set_full_kernel_matrix_from_full(data)
labels=BinaryLabels(lab)
svm=LibSVM(C, kernel, labels)
svm.train()
predictions =svm.apply()
out=svm.apply().get_labels()
return svm,out
def kernel_custom_modular(dim=7):
from numpy.random import rand, seed
from numpy import array, float32, int32
from modshogun import RealFeatures
from modshogun import CustomKernel
from modshogun import IndexFeatures
seed(17)
data = rand(dim, dim)
feats = RealFeatures(data)
symdata = data + data.T
lowertriangle = array([
symdata[(x, y)] for x in range(symdata.shape[1])
for y in range(symdata.shape[0]) if y <= x
])
kernel = CustomKernel()
# once with float64's
kernel.set_triangle_kernel_matrix_from_triangle(lowertriangle)
km_triangletriangle = kernel.get_kernel_matrix()
kernel.set_triangle_kernel_matrix_from_full(symdata)
km_fulltriangle = kernel.get_kernel_matrix()
kernel.set_full_kernel_matrix_from_full(symdata)
km_fullfull = kernel.get_kernel_matrix()
# get subset of kernel
row_idx = array(range(3), dtype=int32)
col_idx = array(range(2), dtype=int32)
row_idx_feat = IndexFeatures(row_idx)
col_idx_feat = IndexFeatures(col_idx)
kernel.init(row_idx_feat, col_idx_feat)
km_sub_kernel = kernel.get_kernel_matrix()
# print('Subkernel(3x2):\n%s'%km_sub_kernel)
kernel.remove_all_col_subsets()
kernel.remove_all_row_subsets()
# now once with float32's
data = array(data, dtype=float32)
kernel.set_triangle_kernel_matrix_from_triangle(lowertriangle)
km_triangletriangle = kernel.get_kernel_matrix()
kernel.set_triangle_kernel_matrix_from_full(symdata)
km_fulltriangle = kernel.get_kernel_matrix()
kernel.set_full_kernel_matrix_from_full(symdata)
km_fullfull = kernel.get_kernel_matrix()
return km_fullfull, kernel, km_sub_kernel
def statistics_quadratic_time_mmd(m, dim, difference):
from modshogun import RealFeatures
from modshogun import MeanShiftDataGenerator
from modshogun import GaussianKernel, CustomKernel
from modshogun import QuadraticTimeMMD
from modshogun import BOOTSTRAP, MMD2_SPECTRUM, MMD2_GAMMA, BIASED, UNBIASED
from modshogun import Statistics, IntVector, RealVector, Math
# init seed for reproducability
Math.init_random(1)
random.seed(17)
# number of examples kept low in order to make things fast
# streaming data generator for mean shift distributions
gen_p = MeanShiftDataGenerator(0, dim)
#gen_p.parallel.set_num_threads(1)
gen_q = MeanShiftDataGenerator(difference, dim)
# stream some data from generator
feat_p = gen_p.get_streamed_features(m)
feat_q = gen_q.get_streamed_features(m)
# set kernel a-priori. usually one would do some kernel selection. See
# other examples for this.
width = 10
kernel = GaussianKernel(10, width)
# create quadratic time mmd instance. Note that this constructor
# copies p and q and does not reference them
mmd = QuadraticTimeMMD(kernel, feat_p, feat_q)
# perform test: compute p-value and test if null-hypothesis is rejected for
# a test level of 0.05
alpha = 0.05
# using bootstrapping (slow, not the most reliable way. Consider pre-
# computing the kernel when using it, see below).
# Also, in practice, use at least 250 iterations
mmd.set_null_approximation_method(BOOTSTRAP)
mmd.set_bootstrap_iterations(3)
p_value_boot = mmd.perform_test()
# reject if p-value is smaller than test level
#print "bootstrap: p!=q: ", p_value_boot<alpha
# using spectrum method. Use at least 250 samples from null.
# This is consistent but sometimes breaks, always monitor type I error.
# See tutorial for number of eigenvalues to use .
# Only works with BIASED statistic
mmd.set_statistic_type(BIASED)
mmd.set_null_approximation_method(MMD2_SPECTRUM)
mmd.set_num_eigenvalues_spectrum(3)
mmd.set_num_samples_sepctrum(250)
p_value_spectrum = mmd.perform_test()
# reject if p-value is smaller than test level
#print "spectrum: p!=q: ", p_value_spectrum<alpha
# using gamma method. This is a quick hack, which works most of the time
# but is NOT guaranteed to. See tutorial for details.
# Only works with BIASED statistic
mmd.set_statistic_type(BIASED)
mmd.set_null_approximation_method(MMD2_GAMMA)
p_value_gamma = mmd.perform_test()
# reject if p-value is smaller than test level
#print "gamma: p!=q: ", p_value_gamma<alpha
# compute tpye I and II error (use many more trials in practice).
# Type I error is not necessary if one uses bootstrapping. We do it here
# anyway, but note that this is an efficient way of computing it.
# Also note that testing has to happen on
# difference data than kernel selection, but the linear time mmd does this
# implicitly and we used a fixed kernel here.
mmd.set_null_approximation_method(BOOTSTRAP)
mmd.set_bootstrap_iterations(5)
num_trials = 5
type_I_errors = RealVector(num_trials)
type_II_errors = RealVector(num_trials)
inds = int32(array([x for x in range(2 * m)])) # numpy
p_and_q = mmd.get_p_and_q()
# use a precomputed kernel to be faster
kernel.init(p_and_q, p_and_q)
precomputed = CustomKernel(kernel)
mmd.set_kernel(precomputed)
for i in range(num_trials):
# this effectively means that p=q - rejecting is tpye I error
inds = random.permutation(inds) # numpy permutation
precomputed.add_row_subset(inds)
precomputed.add_col_subset(inds)
type_I_errors[i] = mmd.perform_test() > alpha
precomputed.remove_row_subset()
precomputed.remove_col_subset()
# on normal data, this gives type II error
type_II_errors[i] = mmd.perform_test() > alpha
return type_I_errors.get(), type_I_errors.get(
), p_value_boot, p_value_spectrum, p_value_gamma,
def statistics_quadratic_time_mmd (m,dim,difference): from modshogun import RealFeatures from modshogun import MeanShiftDataGenerator from modshogun import GaussianKernel, CustomKernel from modshogun import QuadraticTimeMMD from modshogun import PERMUTATION, MMD2_SPECTRUM, MMD2_GAMMA, BIASED, BIASED_DEPRECATED from modshogun import Statistics, IntVector, RealVector, Math # init seed for reproducability Math.init_random(1) random.seed(17) # number of examples kept low in order to make things fast # streaming data generator for mean shift distributions gen_p=MeanShiftDataGenerator(0, dim); #gen_p.parallel.set_num_threads(1) gen_q=MeanShiftDataGenerator(difference, dim); # stream some data from generator feat_p=gen_p.get_streamed_features(m); feat_q=gen_q.get_streamed_features(m); # set kernel a-priori. usually one would do some kernel selection. See # other examples for this. width=10; kernel=GaussianKernel(10, width); # create quadratic time mmd instance. Note that this constructor # copies p and q and does not reference them mmd=QuadraticTimeMMD(kernel, feat_p, feat_q); # perform test: compute p-value and test if null-hypothesis is rejected for # a test level of 0.05 alpha=0.05; # using permutation (slow, not the most reliable way. Consider pre- # computing the kernel when using it, see below). # Also, in practice, use at least 250 iterations mmd.set_null_approximation_method(PERMUTATION); mmd.set_num_null_samples(3); p_value_null=mmd.perform_test(); # reject if p-value is smaller than test level #print "bootstrap: p!=q: ", p_value_null<alpha # using spectrum method. Use at least 250 samples from null. # This is consistent but sometimes breaks, always monitor type I error. # See tutorial for number of eigenvalues to use . mmd.set_statistic_type(BIASED); mmd.set_null_approximation_method(MMD2_SPECTRUM); mmd.set_num_eigenvalues_spectrum(3); mmd.set_num_samples_spectrum(250); p_value_spectrum=mmd.perform_test(); # reject if p-value is smaller than test level #print "spectrum: p!=q: ", p_value_spectrum<alpha # using gamma method. This is a quick hack, which works most of the time # but is NOT guaranteed to. See tutorial for details. # Only works with BIASED_DEPRECATED statistic mmd.set_statistic_type(BIASED_DEPRECATED); mmd.set_null_approximation_method(MMD2_GAMMA); p_value_gamma=mmd.perform_test(); # reject if p-value is smaller than test level #print "gamma: p!=q: ", p_value_gamma<alpha # compute tpye I and II error (use many more trials in practice). # Type I error is not necessary if one uses permutation. We do it here # anyway, but note that this is an efficient way of computing it. # Also note that testing has to happen on # difference data than kernel selection, but the linear time mmd does this # implicitly and we used a fixed kernel here. mmd.set_statistic_type(BIASED); mmd.set_null_approximation_method(PERMUTATION); mmd.set_num_null_samples(5); num_trials=5; type_I_errors=RealVector(num_trials); type_II_errors=RealVector(num_trials); inds=int32(array([x for x in range(2*m)])) # numpy p_and_q=mmd.get_p_and_q(); # use a precomputed kernel to be faster kernel.init(p_and_q, p_and_q); precomputed=CustomKernel(kernel); mmd.set_kernel(precomputed); for i in range(num_trials): # this effectively means that p=q - rejecting is tpye I error inds=random.permutation(inds) # numpy permutation precomputed.add_row_subset(inds); precomputed.add_col_subset(inds); type_I_errors[i]=mmd.perform_test()>alpha; precomputed.remove_row_subset(); precomputed.remove_col_subset(); # on normal data, this gives type II error type_II_errors[i]=mmd.perform_test()>alpha; return type_I_errors.get(),type_I_errors.get(),p_value_null,p_value_spectrum,p_value_gamma,
def mkl_binclass_modular (fm_train_real=traindat,fm_test_real=testdat,fm_label_twoclass = label_traindat):
##################################
# set up and train
# create some poly train/test matrix
tfeats = RealFeatures(fm_train_real)
tkernel = PolyKernel(10,3)
tkernel.init(tfeats, tfeats)
K_train = tkernel.get_kernel_matrix()
pfeats = RealFeatures(fm_test_real)
tkernel.init(tfeats, pfeats)
K_test = tkernel.get_kernel_matrix()
# create combined train features
feats_train = CombinedFeatures()
feats_train.append_feature_obj(RealFeatures(fm_train_real))
# and corresponding combined kernel
kernel = CombinedKernel()
kernel.append_kernel(CustomKernel(K_train))
kernel.append_kernel(PolyKernel(10,2))
kernel.init(feats_train, feats_train)
# train mkl
labels = BinaryLabels(fm_label_twoclass)
mkl = MKLClassification()
# which norm to use for MKL
mkl.set_mkl_norm(1) #2,3
# set cost (neg, pos)
mkl.set_C(1, 1)
# set kernel and labels
mkl.set_kernel(kernel)
mkl.set_labels(labels)
# train
mkl.train()
#w=kernel.get_subkernel_weights()
#kernel.set_subkernel_weights(w)
##################################
# test
# create combined test features
feats_pred = CombinedFeatures()
feats_pred.append_feature_obj(RealFeatures(fm_test_real))
# and corresponding combined kernel
kernel = CombinedKernel()
kernel.append_kernel(CustomKernel(K_test))
kernel.append_kernel(PolyKernel(10, 2))
kernel.init(feats_train, feats_pred)
# and classify
mkl.set_kernel(kernel)
mkl.apply()
return mkl.apply(),kernel
def kernel_custom_modular (dim=7): from numpy.random import rand, seed from numpy import array, float32 from modshogun import RealFeatures from modshogun import CustomKernel seed(17) data=rand(dim, dim) feats=RealFeatures(data) symdata=data+data.T lowertriangle=array([symdata[(x,y)] for x in range(symdata.shape[1]) for y in range(symdata.shape[0]) if y<=x]) kernel=CustomKernel() # once with float64's kernel.set_triangle_kernel_matrix_from_triangle(lowertriangle) km_triangletriangle=kernel.get_kernel_matrix() kernel.set_triangle_kernel_matrix_from_full(symdata) km_fulltriangle=kernel.get_kernel_matrix() kernel.set_full_kernel_matrix_from_full(symdata) km_fullfull=kernel.get_kernel_matrix() # now once with float32's data=array(data,dtype=float32) kernel.set_triangle_kernel_matrix_from_triangle(lowertriangle) km_triangletriangle=kernel.get_kernel_matrix() kernel.set_triangle_kernel_matrix_from_full(symdata) km_fulltriangle=kernel.get_kernel_matrix() kernel.set_full_kernel_matrix_from_full(symdata) km_fullfull=kernel.get_kernel_matrix() return km_fullfull,kernel
def kernel_custom_modular (dim=7):
from numpy.random import rand, seed
from numpy import array, float32, int32
from modshogun import RealFeatures
from modshogun import CustomKernel
from modshogun import IndexFeatures
seed(17)
data=rand(dim, dim)
feats=RealFeatures(data)
symdata=data+data.T
lowertriangle=array([symdata[(x,y)] for x in range(symdata.shape[1])
for y in range(symdata.shape[0]) if y<=x])
kernel=CustomKernel()
# once with float64's
kernel.set_triangle_kernel_matrix_from_triangle(lowertriangle)
km_triangletriangle=kernel.get_kernel_matrix()
kernel.set_triangle_kernel_matrix_from_full(symdata)
km_fulltriangle=kernel.get_kernel_matrix()
kernel.set_full_kernel_matrix_from_full(symdata)
km_fullfull=kernel.get_kernel_matrix()
# get subset of kernel
row_idx=array(range(3),dtype=int32)
col_idx=array(range(2),dtype=int32)
row_idx_feat=IndexFeatures(row_idx)
col_idx_feat=IndexFeatures(col_idx)
kernel.init(row_idx_feat, col_idx_feat)
km_sub_kernel=kernel.get_kernel_matrix()
# print('Subkernel(3x2):\n%s'%km_sub_kernel)
kernel.remove_all_col_subsets()
kernel.remove_all_row_subsets()
# now once with float32's
data=array(data,dtype=float32)
kernel.set_triangle_kernel_matrix_from_triangle(lowertriangle)
km_triangletriangle=kernel.get_kernel_matrix()
kernel.set_triangle_kernel_matrix_from_full(symdata)
km_fulltriangle=kernel.get_kernel_matrix()
kernel.set_full_kernel_matrix_from_full(symdata)
km_fullfull=kernel.get_kernel_matrix()
return km_fullfull,kernel,km_sub_kernel
