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_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 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 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 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 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
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
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
''' this method to whiten the data didn't really work out
