add boost group support to xgboost. now have beta multi-class classification
This commit is contained in:
tqchen
parent
21f93ffd6a
commit
8c0c10463e
@ -88,8 +88,8 @@ namespace xgboost{
|
||||
}
|
||||
}
|
||||
if (mparam.num_pbuffer != 0){
|
||||
pred_buffer.resize(mparam.num_pbuffer);
|
||||
pred_counter.resize(mparam.num_pbuffer);
|
||||
pred_buffer.resize(mparam.PredBufferSize());
|
||||
pred_counter.resize(mparam.PredBufferSize());
|
||||
utils::Assert(fi.Read(&pred_buffer[0], pred_buffer.size()*sizeof(float)) != 0);
|
||||
utils::Assert(fi.Read(&pred_counter[0], pred_counter.size()*sizeof(unsigned)) != 0);
|
||||
}
|
||||
@ -117,8 +117,8 @@ namespace xgboost{
|
||||
*/
|
||||
inline void InitModel(void){
|
||||
pred_buffer.clear(); pred_counter.clear();
|
||||
pred_buffer.resize(mparam.num_pbuffer, 0.0);
|
||||
pred_counter.resize(mparam.num_pbuffer, 0);
|
||||
pred_buffer.resize(mparam.PredBufferSize(), 0.0);
|
||||
pred_counter.resize(mparam.PredBufferSize(), 0);
|
||||
utils::Assert(mparam.num_boosters == 0);
|
||||
utils::Assert(boosters.size() == 0);
|
||||
}
|
||||
@ -130,6 +130,7 @@ namespace xgboost{
|
||||
if (tparam.nthread != 0){
|
||||
omp_set_num_threads(tparam.nthread);
|
||||
}
|
||||
if (mparam.num_booster_group == 0) mparam.num_booster_group = 1;
|
||||
// make sure all the boosters get the latest parameters
|
||||
for (size_t i = 0; i < this->boosters.size(); i++){
|
||||
this->ConfigBooster(this->boosters[i]);
|
||||
@ -175,12 +176,14 @@ namespace xgboost{
|
||||
* \param feats features of each instance
|
||||
* \param root_index pre-partitioned root index of each instance,
|
||||
* root_index.size() can be 0 which indicates that no pre-partition involved
|
||||
* \param bst_group which booster group it belongs to, by default, we only have 1 booster group, and leave this parameter as default
|
||||
*/
|
||||
inline void DoBoost(std::vector<float> &grad,
|
||||
std::vector<float> &hess,
|
||||
const booster::FMatrixS &feats,
|
||||
const std::vector<unsigned> &root_index) {
|
||||
booster::IBooster *bst = this->GetUpdateBooster();
|
||||
const std::vector<unsigned> &root_index,
|
||||
int bst_group = 0 ) {
|
||||
booster::IBooster *bst = this->GetUpdateBooster( bst_group );
|
||||
bst->DoBoost(grad, hess, feats, root_index);
|
||||
}
|
||||
/*!
|
||||
@ -190,26 +193,30 @@ namespace xgboost{
|
||||
* \param row_index row index in the feature matrix
|
||||
* \param buffer_index the buffer index of the current feature line, default -1 means no buffer assigned
|
||||
* \param root_index root id of current instance, default = 0
|
||||
* \param bst_group booster group index
|
||||
* \return prediction
|
||||
*/
|
||||
inline float Predict(const FMatrixS &feats, bst_uint row_index, int buffer_index = -1, unsigned root_index = 0){
|
||||
size_t istart = 0;
|
||||
inline float Predict(const FMatrixS &feats, bst_uint row_index,
|
||||
int buffer_index = -1, unsigned root_index = 0, int bst_group = 0 ){
|
||||
size_t itop = 0;
|
||||
float psum = 0.0f;
|
||||
const int bid = mparam.BufferOffset(buffer_index, bst_group);
|
||||
|
||||
// load buffered results if any
|
||||
if (mparam.do_reboost == 0 && buffer_index >= 0){
|
||||
utils::Assert(buffer_index < mparam.num_pbuffer, "buffer index exceed num_pbuffer");
|
||||
istart = this->pred_counter[buffer_index];
|
||||
psum = this->pred_buffer[buffer_index];
|
||||
if (mparam.do_reboost == 0 && bid >= 0){
|
||||
itop = this->pred_counter[bid];
|
||||
psum = this->pred_buffer[bid];
|
||||
}
|
||||
|
||||
for (size_t i = istart; i < this->boosters.size(); i++){
|
||||
psum += this->boosters[i]->Predict(feats, row_index, root_index);
|
||||
for (size_t i = itop; i < this->boosters.size(); ++i ){
|
||||
if( booster_info[i] == bst_group ){
|
||||
psum += this->boosters[i]->Predict(feats, row_index, root_index);
|
||||
}
|
||||
}
|
||||
// updated the buffered results
|
||||
if (mparam.do_reboost == 0 && buffer_index >= 0){
|
||||
this->pred_counter[buffer_index] = static_cast<unsigned>(boosters.size());
|
||||
this->pred_buffer[buffer_index] = psum;
|
||||
if (mparam.do_reboost == 0 && bid >= 0){
|
||||
this->pred_counter[bid] = static_cast<unsigned>(boosters.size());
|
||||
this->pred_buffer[bid] = psum;
|
||||
}
|
||||
return psum;
|
||||
}
|
||||
@ -217,6 +224,11 @@ namespace xgboost{
|
||||
inline int NumBoosters(void) const{
|
||||
return mparam.num_boosters;
|
||||
}
|
||||
/*! \return number of booster groups */
|
||||
inline int NumBoosterGroup(void) const{
|
||||
if( mparam.num_booster_group == 0 ) return 1;
|
||||
return mparam.num_booster_group;
|
||||
}
|
||||
public:
|
||||
//--------trial code for interactive update an existing booster------
|
||||
//-------- usually not needed, ignore this region ---------
|
||||
@ -224,14 +236,17 @@ namespace xgboost{
|
||||
* \brief same as Predict, but removes the prediction of booster to be updated
|
||||
* this function must be called once and only once for every data with pbuffer
|
||||
*/
|
||||
inline float InteractPredict(const FMatrixS &feats, bst_uint row_index, int buffer_index = -1, unsigned root_index = 0){
|
||||
inline float InteractPredict(const FMatrixS &feats, bst_uint row_index,
|
||||
int buffer_index = -1, unsigned root_index = 0, int bst_group = 0){
|
||||
float psum = this->Predict(feats, row_index, buffer_index, root_index);
|
||||
if (tparam.reupdate_booster != -1){
|
||||
const int bid = tparam.reupdate_booster;
|
||||
utils::Assert(bid >= 0 && bid < (int)boosters.size(), "interact:booster_index exceed existing bound");
|
||||
psum -= boosters[bid]->Predict(feats, row_index, root_index);
|
||||
if( bst_group == booster_info[bid] ){
|
||||
psum -= boosters[bid]->Predict(feats, row_index, root_index);
|
||||
}
|
||||
if (mparam.do_reboost == 0 && buffer_index >= 0){
|
||||
this->pred_buffer[buffer_index] = psum;
|
||||
this->pred_buffer[mparam.BufferOffset(buffer_index,bst_group)] = psum;
|
||||
}
|
||||
}
|
||||
return psum;
|
||||
@ -246,15 +261,21 @@ namespace xgboost{
|
||||
booster_info[i - 1] = booster_info[i];
|
||||
}
|
||||
boosters.resize(mparam.num_boosters -= 1);
|
||||
booster_info.resize(boosters.size());
|
||||
booster_info.resize(boosters.size());
|
||||
// update pred counter
|
||||
for( size_t i = 0; i < pred_counter.size(); ++ i ){
|
||||
if( pred_counter[i] > (unsigned)bid ) pred_counter[i] -= 1;
|
||||
}
|
||||
}
|
||||
/*! \brief update the prediction buffer, after booster have been updated */
|
||||
inline void InteractRePredict(const FMatrixS &feats, bst_uint row_index, int buffer_index = -1, unsigned root_index = 0){
|
||||
inline void InteractRePredict(const FMatrixS &feats, bst_uint row_index,
|
||||
int buffer_index = -1, unsigned root_index = 0, int bst_group = 0 ){
|
||||
if (tparam.reupdate_booster != -1){
|
||||
const int bid = tparam.reupdate_booster;
|
||||
if( booster_info[bid] != bst_group ) return;
|
||||
utils::Assert(bid >= 0 && bid < (int)boosters.size(), "interact:booster_index exceed existing bound");
|
||||
if (mparam.do_reboost == 0 && buffer_index >= 0){
|
||||
this->pred_buffer[buffer_index] += boosters[bid]->Predict(feats, row_index, root_index);
|
||||
this->pred_buffer[mparam.BufferOffset(buffer_index,bst_group)] += boosters[bid]->Predict(feats, row_index, root_index);
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -278,18 +299,19 @@ namespace xgboost{
|
||||
* \brief get a booster to update
|
||||
* \return the booster created
|
||||
*/
|
||||
inline booster::IBooster *GetUpdateBooster(void){
|
||||
inline booster::IBooster *GetUpdateBooster(int bst_group){
|
||||
if (tparam.reupdate_booster != -1){
|
||||
const int bid = tparam.reupdate_booster;
|
||||
utils::Assert(bid >= 0 && bid < (int)boosters.size(), "interact:booster_index exceed existing bound");
|
||||
this->ConfigBooster(boosters[bid]);
|
||||
utils::Assert( bst_group == booster_info[bid], "booster group must match existing reupdate booster");
|
||||
return boosters[bid];
|
||||
}
|
||||
|
||||
if (mparam.do_reboost == 0 || boosters.size() == 0){
|
||||
mparam.num_boosters += 1;
|
||||
boosters.push_back(booster::CreateBooster<FMatrixS>(mparam.booster_type));
|
||||
booster_info.push_back(0);
|
||||
booster_info.push_back(bst_group);
|
||||
this->ConfigBooster(boosters.back());
|
||||
boosters.back()->InitModel();
|
||||
}
|
||||
@ -316,8 +338,13 @@ namespace xgboost{
|
||||
* set to 1 for linear booster, so that regularization term can be considered
|
||||
*/
|
||||
int do_reboost;
|
||||
/*!
|
||||
* \brief number of booster group, how many predictions a single
|
||||
* input instance could corresponds to
|
||||
*/
|
||||
int num_booster_group;
|
||||
/*! \brief reserved parameters */
|
||||
int reserved[32];
|
||||
int reserved[31];
|
||||
/*! \brief constructor */
|
||||
ModelParam(void){
|
||||
num_boosters = 0;
|
||||
@ -325,6 +352,7 @@ namespace xgboost{
|
||||
num_roots = num_feature = 0;
|
||||
do_reboost = 0;
|
||||
num_pbuffer = 0;
|
||||
num_booster_group = 1;
|
||||
memset(reserved, 0, sizeof(reserved));
|
||||
}
|
||||
/*!
|
||||
@ -338,10 +366,21 @@ namespace xgboost{
|
||||
// linear boost automatically set do reboost
|
||||
if (booster_type == 1) do_reboost = 1;
|
||||
}
|
||||
if (!strcmp("num_pbuffer", name)) num_pbuffer = atoi(val);
|
||||
if (!strcmp("do_reboost", name)) do_reboost = atoi(val);
|
||||
if (!strcmp("bst:num_roots", name)) num_roots = atoi(val);
|
||||
if (!strcmp("bst:num_feature", name)) num_feature = atoi(val);
|
||||
if (!strcmp("num_pbuffer", name)) num_pbuffer = atoi(val);
|
||||
if (!strcmp("do_reboost", name)) do_reboost = atoi(val);
|
||||
if (!strcmp("num_booster_group", name)) num_booster_group = atoi(val);
|
||||
if (!strcmp("bst:num_roots", name)) num_roots = atoi(val);
|
||||
if (!strcmp("bst:num_feature", name)) num_feature = atoi(val);
|
||||
}
|
||||
inline int PredBufferSize(void) const{
|
||||
if (num_booster_group == 0) return num_pbuffer;
|
||||
else return num_booster_group * num_pbuffer;
|
||||
}
|
||||
inline int BufferOffset( int buffer_index, int bst_group ) const{
|
||||
if( buffer_index < 0 ) return -1;
|
||||
utils::Assert( buffer_index < num_pbuffer, "buffer_indexexceed num_pbuffer" );
|
||||
return buffer_index + num_pbuffer * bst_group;
|
||||
|
||||
}
|
||||
};
|
||||
/*! \brief training parameters */
|
||||
|
||||
@ -86,6 +86,7 @@ namespace xgboost{
|
||||
if (!strcmp(name, "silent")) silent = atoi(val);
|
||||
if (!strcmp(name, "eval_metric")) evaluator_.AddEval(val);
|
||||
if (!strcmp(name, "objective") ) name_obj_ = val;
|
||||
if (!strcmp(name, "num_class") ) base_gbm.SetParam("num_booster_group", val );
|
||||
mparam.SetParam(name, val);
|
||||
base_gbm.SetParam(name, val);
|
||||
cfg_.push_back( std::make_pair( std::string(name), std::string(val) ) );
|
||||
@ -95,7 +96,13 @@ namespace xgboost{
|
||||
* this function is reserved for solver to allocate necessary space and do other preparation
|
||||
*/
|
||||
inline void InitTrainer(void){
|
||||
base_gbm.InitTrainer();
|
||||
if( mparam.num_class != 0 ){
|
||||
if( name_obj_ != "softmax" ){
|
||||
name_obj_ = "softmax";
|
||||
printf("auto select objective=softmax to support multi-class classification\n" );
|
||||
}
|
||||
}
|
||||
base_gbm.InitTrainer();
|
||||
obj_ = CreateObjFunction( name_obj_.c_str() );
|
||||
for( size_t i = 0; i < cfg_.size(); ++ i ){
|
||||
obj_->SetParam( cfg_[i].first.c_str(), cfg_[i].second.c_str() );
|
||||
@ -166,9 +173,18 @@ namespace xgboost{
|
||||
inline void UpdateOneIter(const DMatrix &train){
|
||||
this->PredictRaw(preds_, train);
|
||||
obj_->GetGradient(preds_, train.info, base_gbm.NumBoosters(), grad_, hess_);
|
||||
// do boost
|
||||
std::vector<unsigned> root_index;
|
||||
base_gbm.DoBoost(grad_, hess_, train.data, root_index);
|
||||
if( grad_.size() == train.Size() ){
|
||||
base_gbm.DoBoost(grad_, hess_, train.data, train.info.root_index);
|
||||
}else{
|
||||
int ngroup = base_gbm.NumBoosterGroup();
|
||||
utils::Assert( grad_.size() == train.Size() * (size_t)ngroup, "BUG: UpdateOneIter: mclass" );
|
||||
std::vector<float> tgrad( train.Size() ), thess( train.Size() );
|
||||
for( int g = 0; g < ngroup; ++ g ){
|
||||
memcpy( &tgrad[0], &grad_[g*tgrad.size()], sizeof(float)*tgrad.size() );
|
||||
memcpy( &thess[0], &hess_[g*tgrad.size()], sizeof(float)*tgrad.size() );
|
||||
base_gbm.DoBoost(tgrad, thess, train.data, train.info.root_index, g );
|
||||
}
|
||||
}
|
||||
}
|
||||
/*!
|
||||
* \brief evaluate the model for specific iteration
|
||||
@ -190,9 +206,14 @@ namespace xgboost{
|
||||
fprintf(fo, "\n");
|
||||
fflush(fo);
|
||||
}
|
||||
/*! \brief get prediction, without buffering */
|
||||
inline void Predict(std::vector<float> &preds, const DMatrix &data){
|
||||
this->PredictRaw(preds,data);
|
||||
/*!
|
||||
* \brief get prediction
|
||||
* \param storage to store prediction
|
||||
* \param data input data
|
||||
* \param bst_group booster group we are in
|
||||
*/
|
||||
inline void Predict(std::vector<float> &preds, const DMatrix &data, int bst_group = -1){
|
||||
this->PredictRaw( preds, data, bst_group );
|
||||
obj_->PredTransform( preds );
|
||||
}
|
||||
public:
|
||||
@ -243,22 +264,31 @@ namespace xgboost{
|
||||
}
|
||||
private:
|
||||
/*! \brief get un-transformed prediction*/
|
||||
inline void PredictRaw(std::vector<float> &preds, const DMatrix &data){
|
||||
this->PredictBuffer(preds, data, this->FindBufferOffset(data) );
|
||||
inline void PredictRaw(std::vector<float> &preds, const DMatrix &data, int bst_group = -1 ){
|
||||
int buffer_offset = this->FindBufferOffset(data);
|
||||
if( bst_group < 0 ){
|
||||
int ngroup = base_gbm.NumBoosterGroup();
|
||||
preds.resize( data.Size() * ngroup );
|
||||
for( int g = 0; g < ngroup; ++ g ){
|
||||
this->PredictBuffer(&preds[ data.Size() * g ], data, buffer_offset, g );
|
||||
}
|
||||
}else{
|
||||
preds.resize( data.Size() );
|
||||
this->PredictBuffer(&preds[0], data, buffer_offset, bst_group );
|
||||
}
|
||||
}
|
||||
/*! \brief get the un-transformed predictions, given data */
|
||||
inline void PredictBuffer(std::vector<float> &preds, const DMatrix &data, int buffer_offset){
|
||||
preds.resize(data.Size());
|
||||
inline void PredictBuffer(float *preds, const DMatrix &data, int buffer_offset, int bst_group ){
|
||||
const unsigned ndata = static_cast<unsigned>(data.Size());
|
||||
if( buffer_offset >= 0 ){
|
||||
#pragma omp parallel for schedule( static )
|
||||
for (unsigned j = 0; j < ndata; ++j){
|
||||
preds[j] = mparam.base_score + base_gbm.Predict(data.data, j, buffer_offset + j);
|
||||
preds[j] = mparam.base_score + base_gbm.Predict(data.data, j, buffer_offset + j, data.info.GetRoot(j), bst_group );
|
||||
}
|
||||
}else
|
||||
#pragma omp parallel for schedule( static )
|
||||
for (unsigned j = 0; j < ndata; ++j){
|
||||
preds[j] = mparam.base_score + base_gbm.Predict(data.data, j, -1);
|
||||
preds[j] = mparam.base_score + base_gbm.Predict(data.data, j, -1, data.info.GetRoot(j), bst_group );
|
||||
}{
|
||||
}
|
||||
}
|
||||
@ -270,14 +300,17 @@ namespace xgboost{
|
||||
/* \brief type of loss function */
|
||||
int loss_type;
|
||||
/* \brief number of features */
|
||||
int num_feature;
|
||||
int num_feature;
|
||||
/* \brief number of class, if it is multi-class classification */
|
||||
int num_class;
|
||||
/*! \brief reserved field */
|
||||
int reserved[16];
|
||||
int reserved[15];
|
||||
/*! \brief constructor */
|
||||
ModelParam(void){
|
||||
base_score = 0.5f;
|
||||
loss_type = 0;
|
||||
num_feature = 0;
|
||||
num_class = 0;
|
||||
memset(reserved, 0, sizeof(reserved));
|
||||
}
|
||||
/*!
|
||||
@ -288,6 +321,7 @@ namespace xgboost{
|
||||
inline void SetParam(const char *name, const char *val){
|
||||
if (!strcmp("base_score", name)) base_score = (float)atof(val);
|
||||
if (!strcmp("loss_type", name)) loss_type = atoi(val);
|
||||
if (!strcmp("num_class", name)) num_class = atoi(val);
|
||||
if (!strcmp("bst:num_feature", name)) num_feature = atoi(val);
|
||||
}
|
||||
/*!
|
||||
|
||||
@ -35,11 +35,17 @@ namespace xgboost{
|
||||
std::vector<unsigned> group_ptr;
|
||||
/*! \brief weights of each instance, optional */
|
||||
std::vector<float> weights;
|
||||
/*! \brief specified root index of each instance, can be used for multi task setting*/
|
||||
std::vector<unsigned> root_index;
|
||||
/*! \brief get weight of each instances */
|
||||
inline float GetWeight( size_t i ) const{
|
||||
if( weights.size() != 0 ) return weights[i];
|
||||
if( weights.size() != 0 ) return weights[i];
|
||||
else return 1.0f;
|
||||
}
|
||||
inline float GetRoot( size_t i ) const{
|
||||
if( root_index.size() != 0 ) return root_index[i];
|
||||
else return 0;
|
||||
}
|
||||
};
|
||||
public:
|
||||
/*! \brief feature data content */
|
||||
|
||||
@ -13,6 +13,7 @@
|
||||
#include "../utils/xgboost_omp.h"
|
||||
#include "../utils/xgboost_random.h"
|
||||
#include "xgboost_regrank_data.h"
|
||||
#include "xgboost_regrank_utils.h"
|
||||
|
||||
namespace xgboost{
|
||||
namespace regrank{
|
||||
@ -31,17 +32,11 @@ namespace xgboost{
|
||||
virtual ~IEvaluator(void){}
|
||||
};
|
||||
|
||||
inline static bool CmpFirst(const std::pair<float, unsigned> &a, const std::pair<float, unsigned> &b){
|
||||
return a.first > b.first;
|
||||
}
|
||||
inline static bool CmpSecond(const std::pair<float, unsigned> &a, const std::pair<float, unsigned> &b){
|
||||
return a.second > b.second;
|
||||
}
|
||||
|
||||
/*! \brief RMSE */
|
||||
struct EvalRMSE : public IEvaluator{
|
||||
virtual float Eval(const std::vector<float> &preds,
|
||||
const DMatrix::Info &info) const {
|
||||
utils::Assert( preds.size() == info.labels.size(), "label size predict size not match" );
|
||||
const unsigned ndata = static_cast<unsigned>(preds.size());
|
||||
float sum = 0.0, wsum = 0.0;
|
||||
#pragma omp parallel for reduction(+:sum,wsum) schedule( static )
|
||||
@ -62,6 +57,7 @@ namespace xgboost{
|
||||
struct EvalLogLoss : public IEvaluator{
|
||||
virtual float Eval(const std::vector<float> &preds,
|
||||
const DMatrix::Info &info) const {
|
||||
utils::Assert( preds.size() == info.labels.size(), "label size predict size not match" );
|
||||
const unsigned ndata = static_cast<unsigned>(preds.size());
|
||||
float sum = 0.0f, wsum = 0.0f;
|
||||
#pragma omp parallel for reduction(+:sum,wsum) schedule( static )
|
||||
@ -106,7 +102,8 @@ namespace xgboost{
|
||||
/*! \brief Area under curve, for both classification and rank */
|
||||
struct EvalAuc : public IEvaluator{
|
||||
virtual float Eval(const std::vector<float> &preds,
|
||||
const DMatrix::Info &info) const {
|
||||
const DMatrix::Info &info) const {
|
||||
utils::Assert( preds.size() == info.labels.size(), "label size predict size not match" );
|
||||
std::vector<unsigned> tgptr(2, 0); tgptr[1] = preds.size();
|
||||
const std::vector<unsigned> &gptr = info.group_ptr.size() == 0 ? tgptr : info.group_ptr;
|
||||
utils::Assert(gptr.back() == preds.size(), "EvalAuc: group structure must match number of prediction");
|
||||
@ -159,6 +156,7 @@ namespace xgboost{
|
||||
public:
|
||||
virtual float Eval(const std::vector<float> &preds,
|
||||
const DMatrix::Info &info) const {
|
||||
utils::Assert( preds.size() == info.labels.size(), "label size predict size not match" );
|
||||
const std::vector<unsigned> &gptr = info.group_ptr;
|
||||
utils::Assert(gptr.size() != 0 && gptr.back() == preds.size(), "EvalAuc: group structure must match number of prediction");
|
||||
const unsigned ngroup = static_cast<unsigned>(gptr.size() - 1);
|
||||
|
||||
@ -106,8 +106,9 @@ namespace xgboost{
|
||||
namespace regrank{
|
||||
IObjFunction* CreateObjFunction( const char *name ){
|
||||
if( !strcmp("reg", name ) ) return new RegressionObj();
|
||||
if( !strcmp("rank", name ) ) return new PairwiseRankObj();
|
||||
if( !strcmp("softmax", name ) ) return new SoftmaxObj();
|
||||
if( !strcmp("rank:pairwise", name ) ) return new PairwiseRankObj();
|
||||
if( !strcmp("rank:softmax", name ) ) return new SoftmaxRankObj();
|
||||
if( !strcmp("softmax", name ) ) return new SoftmaxMultiClassObj();
|
||||
utils::Error("unknown objective function type");
|
||||
return NULL;
|
||||
}
|
||||
|
||||
@ -1,12 +1,13 @@
|
||||
#ifndef XGBOOST_REGRANK_OBJ_HPP
|
||||
#define XGBOOST_REGRANK_OBJ_HPP
|
||||
/*!
|
||||
* \file xgboost_regrank_obj.h
|
||||
* \file xgboost_regrank_obj.hpp
|
||||
* \brief implementation of objective functions
|
||||
* \author Tianqi Chen, Kailong Chen
|
||||
*/
|
||||
//#include "xgboost_regrank_sample.h"
|
||||
#include <vector>
|
||||
#include "xgboost_regrank_utils.h"
|
||||
|
||||
namespace xgboost{
|
||||
namespace regrank{
|
||||
@ -24,6 +25,7 @@ namespace xgboost{
|
||||
int iter,
|
||||
std::vector<float> &grad,
|
||||
std::vector<float> &hess ) {
|
||||
utils::Assert( preds.size() == info.labels.size(), "label size predict size not match" );
|
||||
grad.resize(preds.size()); hess.resize(preds.size());
|
||||
|
||||
const unsigned ndata = static_cast<unsigned>(preds.size());
|
||||
@ -52,11 +54,11 @@ namespace xgboost{
|
||||
|
||||
namespace regrank{
|
||||
// simple softmax rak
|
||||
class SoftmaxObj : public IObjFunction{
|
||||
class SoftmaxRankObj : public IObjFunction{
|
||||
public:
|
||||
SoftmaxObj(void){
|
||||
SoftmaxRankObj(void){
|
||||
}
|
||||
virtual ~SoftmaxObj(){}
|
||||
virtual ~SoftmaxRankObj(){}
|
||||
virtual void SetParam(const char *name, const char *val){
|
||||
}
|
||||
virtual void GetGradient(const std::vector<float>& preds,
|
||||
@ -64,6 +66,7 @@ namespace xgboost{
|
||||
int iter,
|
||||
std::vector<float> &grad,
|
||||
std::vector<float> &hess ) {
|
||||
utils::Assert( preds.size() == info.labels.size(), "label size predict size not match" );
|
||||
grad.resize(preds.size()); hess.resize(preds.size());
|
||||
const std::vector<unsigned> &gptr = info.group_ptr;
|
||||
utils::Assert( gptr.size() != 0 && gptr.back() == preds.size(), "rank loss must have group file" );
|
||||
@ -96,23 +99,76 @@ namespace xgboost{
|
||||
}
|
||||
virtual const char* DefaultEvalMetric(void) {
|
||||
return "pre@1";
|
||||
}
|
||||
private:
|
||||
inline static void Softmax( std::vector<float>& rec ){
|
||||
float wmax = rec[0];
|
||||
for( size_t i = 1; i < rec.size(); ++ i ){
|
||||
wmax = std::max( rec[i], wmax );
|
||||
}
|
||||
double wsum = 0.0f;
|
||||
for( size_t i = 0; i < rec.size(); ++ i ){
|
||||
rec[i] = expf(rec[i]-wmax);
|
||||
wsum += rec[i];
|
||||
}
|
||||
for( size_t i = 0; i < rec.size(); ++ i ){
|
||||
rec[i] /= wsum;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
// simple softmax multi-class classification
|
||||
class SoftmaxMultiClassObj : public IObjFunction{
|
||||
public:
|
||||
SoftmaxMultiClassObj(void){
|
||||
nclass = 0;
|
||||
}
|
||||
virtual ~SoftmaxMultiClassObj(){}
|
||||
virtual void SetParam(const char *name, const char *val){
|
||||
if( !strcmp( "num_class", name ) ) nclass = atoi(val);
|
||||
}
|
||||
virtual void GetGradient(const std::vector<float>& preds,
|
||||
const DMatrix::Info &info,
|
||||
int iter,
|
||||
std::vector<float> &grad,
|
||||
std::vector<float> &hess ) {
|
||||
utils::Assert( nclass != 0, "must set num_class to use softmax" );
|
||||
utils::Assert( preds.size() == (size_t)nclass * info.labels.size(), "SoftmaxMultiClassObj: label size and pred size does not match" );
|
||||
grad.resize(preds.size()); hess.resize(preds.size());
|
||||
|
||||
const unsigned ndata = static_cast<unsigned>(info.labels.size());
|
||||
#pragma omp parallel
|
||||
{
|
||||
std::vector<float> rec(nclass);
|
||||
#pragma for schedule(static)
|
||||
for (unsigned j = 0; j < ndata; ++j){
|
||||
for( int k = 0; k < nclass; ++ k ){
|
||||
rec[k] = preds[j + k * ndata];
|
||||
}
|
||||
Softmax( rec );
|
||||
int label = static_cast<int>(info.labels[j]);
|
||||
utils::Assert( label < nclass, "SoftmaxMultiClassObj: label exceed num_class" );
|
||||
for( int k = 0; k < nclass; ++ k ){
|
||||
float p = rec[ k ];
|
||||
if( label == k ){
|
||||
grad[j+k*ndata] = p - 1.0f;
|
||||
}else{
|
||||
grad[j+k*ndata] = p;
|
||||
}
|
||||
hess[j+k*ndata] = 2.0f * p * ( 1.0f - p );
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
virtual void PredTransform(std::vector<float> &preds){
|
||||
utils::Assert( nclass != 0, "must set num_class to use softmax" );
|
||||
utils::Assert( preds.size() % nclass == 0, "SoftmaxMultiClassObj: label size and pred size does not match" );
|
||||
const unsigned ndata = static_cast<unsigned>(preds.size()/nclass);
|
||||
#pragma omp parallel
|
||||
{
|
||||
std::vector<float> rec(nclass);
|
||||
#pragma for schedule(static)
|
||||
for (unsigned j = 0; j < ndata; ++j){
|
||||
for( int k = 0; k < nclass; ++ k ){
|
||||
rec[k] = preds[j + k * ndata];
|
||||
}
|
||||
Softmax( rec );
|
||||
preds[j] = FindMaxIndex( rec );
|
||||
}
|
||||
}
|
||||
preds.resize( ndata );
|
||||
}
|
||||
virtual const char* DefaultEvalMetric(void) {
|
||||
return "error";
|
||||
}
|
||||
private:
|
||||
int nclass;
|
||||
};
|
||||
};
|
||||
|
||||
namespace regrank{
|
||||
@ -133,6 +189,7 @@ namespace xgboost{
|
||||
int iter,
|
||||
std::vector<float> &grad,
|
||||
std::vector<float> &hess ) {
|
||||
utils::Assert( preds.size() == info.labels.size(), "label size predict size not match" );
|
||||
grad.resize(preds.size()); hess.resize(preds.size());
|
||||
const std::vector<unsigned> &gptr = info.group_ptr;
|
||||
utils::Assert( gptr.size() != 0 && gptr.back() == preds.size(), "rank loss must have group file" );
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user