Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #367 from karlnapf/master
A draft for training on fixed kernel matrices/data in general
- Loading branch information
Showing
31 changed files
with
953 additions
and
93 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
150 changes: 150 additions & 0 deletions
150
examples/undocumented/libshogun/evaluation_cross_validation_locked_comparison.cpp
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,150 @@ | ||
/* | ||
* This program is free software; you can redistribute it and/or modify | ||
* it under the terms of the GNU General Public License as published by | ||
* the Free Software Foundation; either version 3 of the License, or | ||
* (at your option) any later version. | ||
* | ||
* Written (W) 2012 Heiko Strathmann | ||
* Copyright (C) 2012 Berlin Institute of Technology and Max-Planck-Society | ||
*/ | ||
|
||
#include <shogun/base/init.h> | ||
#include <shogun/features/SimpleFeatures.h> | ||
#include <shogun/features/Labels.h> | ||
#include <shogun/kernel/GaussianKernel.h> | ||
#include <shogun/classifier/svm/LibSVM.h> | ||
#include <shogun/classifier/svm/SVMLight.h> | ||
#include <shogun/evaluation/CrossValidation.h> | ||
#include <shogun/evaluation/StratifiedCrossValidationSplitting.h> | ||
#include <shogun/evaluation/ContingencyTableEvaluation.h> | ||
#include <shogun/lib/Time.h> | ||
|
||
using namespace shogun; | ||
|
||
void print_message(FILE* target, const char* str) | ||
{ | ||
fprintf(target, "%s", str); | ||
} | ||
|
||
void test_cross_validation() | ||
{ | ||
/* data matrix dimensions */ | ||
index_t num_vectors=500; | ||
index_t num_features=50; | ||
|
||
/* data means -1, 1 in all components, std deviation of sigma */ | ||
SGVector<float64_t> mean_1(num_features); | ||
SGVector<float64_t> mean_2(num_features); | ||
CMath::fill_vector(mean_1.vector, mean_1.vlen, -1.0); | ||
CMath::fill_vector(mean_2.vector, mean_2.vlen, 1.0); | ||
float64_t sigma=1.5; | ||
|
||
/* fill data matrix around mean */ | ||
SGMatrix<float64_t> train_dat(num_features, num_vectors); | ||
for (index_t i=0; i<num_vectors; ++i) | ||
{ | ||
for (index_t j=0; j<num_features; ++j) | ||
{ | ||
float64_t mean=i<num_vectors/2 ? mean_1.vector[0] : mean_2.vector[0]; | ||
train_dat.matrix[i*num_features+j]=CMath::normal_random(mean, sigma); | ||
} | ||
} | ||
|
||
/* training features */ | ||
CSimpleFeatures<float64_t>* features= | ||
new CSimpleFeatures<float64_t>(train_dat); | ||
SG_REF(features); | ||
|
||
/* training labels +/- 1 for each cluster */ | ||
SGVector<float64_t> lab(num_vectors); | ||
for (index_t i=0; i<num_vectors; ++i) | ||
lab.vector[i]=i<num_vectors/2 ? -1.0 : 1.0; | ||
|
||
CLabels* labels=new CLabels(lab); | ||
|
||
/* gaussian kernel */ | ||
CGaussianKernel* kernel=new CGaussianKernel(); | ||
kernel->set_width(10); | ||
kernel->init(features, features); | ||
|
||
/* create svm via libsvm */ | ||
float64_t svm_C=1; | ||
float64_t svm_eps=0.0001; | ||
CSVM* svm=new CLibSVM(svm_C, kernel, labels); | ||
svm->set_epsilon(svm_eps); | ||
|
||
/* train and output the normal way */ | ||
SG_SPRINT("starting normal training\n"); | ||
svm->train(features); | ||
CLabels* output=svm->apply(features); | ||
|
||
/* evaluation criterion */ | ||
CContingencyTableEvaluation* eval_crit= | ||
new CContingencyTableEvaluation(ACCURACY); | ||
|
||
/* evaluate training error */ | ||
float64_t eval_result=eval_crit->evaluate(output, labels); | ||
SG_SPRINT("training accuracy: %f\n", eval_result); | ||
SG_UNREF(output); | ||
|
||
/* assert that regression "works". this is not guaranteed to always work | ||
* but should be a really coarse check to see if everything is going | ||
* approx. right */ | ||
ASSERT(eval_result<2); | ||
|
||
/* splitting strategy */ | ||
index_t n_folds=5; | ||
CStratifiedCrossValidationSplitting* splitting= | ||
new CStratifiedCrossValidationSplitting(labels, n_folds); | ||
|
||
/* cross validation instance, 10 runs, 95% confidence interval */ | ||
CCrossValidation* cross=new CCrossValidation(svm, features, labels, | ||
splitting, eval_crit); | ||
|
||
cross->set_num_runs(20); | ||
cross->set_conf_int_alpha(0.05); | ||
|
||
/* actual evaluation without fixex kernel matrix */ | ||
|
||
index_t repetitions=1; | ||
SG_SPRINT("unlocked x-val\n"); | ||
kernel->init(features, features); | ||
for (index_t i=0; i<repetitions; ++i) | ||
{ | ||
CTime time; | ||
time.start(); | ||
cross->evaluate().print_result(); | ||
time.stop(); | ||
SG_SPRINT("%f sec\n", time.cur_time_diff()); | ||
} | ||
|
||
/* actual evaluation with five kernel matrix (restore features first) */ | ||
svm->data_lock(features, labels); | ||
SG_SPRINT("locked x-val\n"); | ||
for (index_t i=0; i<repetitions; ++i) | ||
{ | ||
CTime time; | ||
time.start(); | ||
cross->evaluate().print_result(); | ||
time.stop(); | ||
SG_SPRINT("%f sec\n", time.cur_time_diff()); | ||
} | ||
|
||
/* clean up */ | ||
SG_UNREF(cross); | ||
SG_UNREF(features); | ||
mean_1.destroy_vector(); | ||
mean_2.destroy_vector(); | ||
} | ||
|
||
int main(int argc, char **argv) | ||
{ | ||
init_shogun(&print_message, &print_message, &print_message); | ||
|
||
test_cross_validation(); | ||
|
||
exit_shogun(); | ||
|
||
return 0; | ||
} | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
150 changes: 150 additions & 0 deletions
150
examples/undocumented/libshogun/kernel_machine_train_locked.cpp
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,150 @@ | ||
/* | ||
* This program is free software; you can redistribute it and/or modify | ||
* it under the terms of the GNU General Public License as published by | ||
* the Free Software Foundation; either version 3 of the License, or | ||
* (at your option) any later version. | ||
* | ||
* Written (W) 2012 Heiko Strathmann | ||
* Copyright (C) 2012 Berlin Institute of Technology and Max-Planck-Society | ||
*/ | ||
|
||
#include <shogun/base/init.h> | ||
#include <shogun/features/SimpleFeatures.h> | ||
#include <shogun/features/Labels.h> | ||
#include <shogun/kernel/LinearKernel.h> | ||
#include <shogun/classifier/svm/LibSVM.h> | ||
#include <shogun/evaluation/ContingencyTableEvaluation.h> | ||
|
||
using namespace shogun; | ||
|
||
void print_message(FILE* target, const char* str) | ||
{ | ||
fprintf(target, "%s", str); | ||
} | ||
|
||
void test() | ||
{ | ||
/* data matrix dimensions */ | ||
index_t num_vectors=6; | ||
index_t num_features=2; | ||
|
||
/* data means -1, 1 in all components, std deviation of 3 */ | ||
SGVector<float64_t> mean_1(num_features); | ||
SGVector<float64_t> mean_2(num_features); | ||
CMath::fill_vector(mean_1.vector, mean_1.vlen, -10.0); | ||
CMath::fill_vector(mean_2.vector, mean_2.vlen, 10.0); | ||
float64_t sigma=0.5; | ||
|
||
CMath::display_vector(mean_1.vector, mean_1.vlen, "mean 1"); | ||
CMath::display_vector(mean_2.vector, mean_2.vlen, "mean 2"); | ||
|
||
/* fill data matrix around mean */ | ||
SGMatrix<float64_t> train_dat(num_features, num_vectors); | ||
for (index_t i=0; i<num_vectors; ++i) | ||
{ | ||
for (index_t j=0; j<num_features; ++j) | ||
{ | ||
float64_t mean=i<num_vectors/2 ? mean_1.vector[0] : mean_2.vector[0]; | ||
train_dat.matrix[i*num_features+j]=CMath::normal_random(mean, sigma); | ||
} | ||
} | ||
|
||
CMath::display_matrix(train_dat.matrix, train_dat.num_rows, train_dat.num_cols, "training data"); | ||
|
||
/* training features */ | ||
CSimpleFeatures<float64_t>* features= | ||
new CSimpleFeatures<float64_t>(train_dat); | ||
SG_REF(features); | ||
|
||
/* training labels +/- 1 for each cluster */ | ||
SGVector<float64_t> lab(num_vectors); | ||
for (index_t i=0; i<num_vectors; ++i) | ||
lab.vector[i]=i<num_vectors/2 ? -1.0 : 1.0; | ||
|
||
CMath::display_vector(lab.vector, lab.vlen, "training labels"); | ||
|
||
CLabels* labels=new CLabels(lab); | ||
SG_REF(labels); | ||
|
||
/* evaluation instance */ | ||
CContingencyTableEvaluation* eval=new CContingencyTableEvaluation(ACCURACY); | ||
|
||
/* kernel */ | ||
CKernel* kernel=new CLinearKernel(); | ||
kernel->init(features, features); | ||
|
||
/* create svm via libsvm */ | ||
float64_t svm_C=10; | ||
float64_t svm_eps=0.0001; | ||
CLibSVM* svm=new CLibSVM(svm_C, kernel, labels); | ||
svm->set_epsilon(svm_eps); | ||
|
||
/* now train a few times on different subsets on data and assert that | ||
* results are correc (data linear separable) */ | ||
|
||
svm->data_lock(features, labels); | ||
|
||
SGVector<index_t> indices(4); | ||
indices.vector[0]=1; | ||
indices.vector[1]=2; | ||
indices.vector[2]=3; | ||
indices.vector[3]=4; | ||
CMath::display_vector(indices.vector, indices.vlen, "training indices"); | ||
svm->train_locked(indices); | ||
CLabels* output=svm->apply(); | ||
ASSERT(eval->evaluate(output, labels)==1); | ||
CMath::display_vector(output->get_labels().vector, output->get_num_labels(), "apply() output"); | ||
SG_UNREF(output); | ||
|
||
SG_SPRINT("\n\n"); | ||
indices.destroy_vector(); | ||
indices=SGVector<index_t>(3); | ||
indices.vector[0]=1; | ||
indices.vector[1]=2; | ||
indices.vector[2]=3; | ||
CMath::display_vector(indices.vector, indices.vlen, "training indices"); | ||
output=svm->apply(); | ||
ASSERT(eval->evaluate(output, labels)==1); | ||
CMath::display_vector(output->get_labels().vector, output->get_num_labels(), "apply() output"); | ||
SG_UNREF(output); | ||
|
||
SG_SPRINT("\n\n"); | ||
indices.destroy_vector(); | ||
indices=SGVector<index_t>(4); | ||
indices.range_fill(); | ||
CMath::display_vector(indices.vector, indices.vlen, "training indices"); | ||
svm->train_locked(indices); | ||
output=svm->apply(); | ||
ASSERT(eval->evaluate(output, labels)==1); | ||
CMath::display_vector(output->get_labels().vector, output->get_num_labels(), "apply() output"); | ||
SG_UNREF(output); | ||
|
||
SG_SPRINT("normal train\n"); | ||
svm->data_unlock(); | ||
svm->train(); | ||
output=svm->apply(); | ||
ASSERT(eval->evaluate(output, labels)==1); | ||
CMath::display_vector(output->get_labels().vector, output->get_num_labels(), "output"); | ||
SG_UNREF(output); | ||
|
||
/* clean up */ | ||
SG_UNREF(svm); | ||
SG_UNREF(features); | ||
SG_UNREF(eval); | ||
SG_UNREF(labels); | ||
mean_1.destroy_vector(); | ||
mean_2.destroy_vector(); | ||
indices.destroy_vector(); | ||
} | ||
|
||
int main(int argc, char **argv) | ||
{ | ||
init_shogun(&print_message, &print_message, &print_message); | ||
|
||
test(); | ||
|
||
exit_shogun(); | ||
|
||
return 0; | ||
} | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.