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 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 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 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 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)
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 PERMUTATION, HSIC_GAMMA
from modshogun import EuclideanDistance
from modshogun import Statistics, Math
# for reproducable results (the numpy one might not be reproducible across
# different OS/Python-distributions
Math.init_random(1)
np.random.seed(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(np.array([data[0]]))
features_y = RealFeatures(np.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 = np.random.permutation(features_x.get_num_vectors()).astype(
np.int32)
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)
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 sampling null"
hsic.set_null_approximation_method(PERMUTATION)
# normally, at least 250 iterations should be done, but that takes long
hsic.set_num_null_samples(100)
# sampling null 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
# sampling null, biased statistic
#print "sampling null distribution using sample_null"
hsic.set_null_approximation_method(PERMUTATION)
hsic.set_num_null_samples(100)
null_samples = hsic.sample_null()
#print "null mean:", np.mean(null_samples)
#print "null variance:", np.var(null_samples)
#hist(null_samples, 100); show()
return p_value_boot, thresh_boot, p_value_gamma, thresh_gamma, statistic, null_samples
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)
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