Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

lambda rank added

Browse Source
This commit is contained in:
kalenhaha
2014-04-10 22:09:19 +08:00
parent 1136c71e64
commit f83942d3e9
18 changed files with 1792 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
dev/base/xgboost_boost_task.h
View File

@@ -174,7 +174,7 @@ namespace xgboost{
inline void InitLearner(void){
cfg.BeforeFirst();
while (cfg.Next()){
learner_->SetParam(cfg.name(), cfg.val());
learner_->SetParam(cfg.name(), cfg.val());
}
if (model_in != "NULL"){
utils::FileStream fi(utils::FopenCheck(model_in.c_str(), "rb"));

18
dev/base/xgboost_data_instance.h
View File

@@ -10,8 +10,8 @@
namespace xgboost{
namespace base{
/*! \brief data matrix for regression,classification,rank content */
struct DMatrix{
/*! \brief data matrix for regression, classification, rank content */
struct DMatrix{
public:
/*! \brief maximum feature dimension */
unsigned num_feature;
@@ -74,7 +74,7 @@ namespace xgboost{
}
inline void LoadGroup(const char* fgroup, bool silent = false){
//if exists group data load it in
//if exists group data load it in
FILE *file_group = fopen64(fgroup, "r");
if (file_group != NULL){
@@ -117,6 +117,7 @@ namespace xgboost{
LoadGroupBinary(fgroup,silent);
return true;
}
/*!
* \brief save to binary file
* \param fname name of binary data
@@ -139,7 +140,7 @@ namespace xgboost{
}
inline void SaveGroupBinary(const char* fgroup, bool silent = false){
//save group data
//save group data
if (group_index.size() > 0){
utils::FileStream file_group(utils::FopenCheck(fgroup, "wb"));
int group_index_size = group_index.size();
@@ -151,7 +152,7 @@ namespace xgboost{
}
inline void LoadGroupBinary(const char* fgroup, bool silent = false){
//if group data exists load it in
//if group data exists load it in
FILE *file_group = fopen64(fgroup, "r");
if (file_group != NULL){
int group_index_size = 0;
@@ -168,8 +169,8 @@ namespace xgboost{
}else{
if(!silent){printf("The binary file of group info not exists");}
}
}
}
/*!
* \brief cache load data given a file name, if filename ends with .buffer, direct load binary
* otherwise the function will first check if fname + '.buffer' exists,
@@ -207,9 +208,6 @@ namespace xgboost{
}
}
};
}
};

26
dev/base/xgboost_learner.h
View File

@@ -144,17 +144,24 @@ namespace xgboost {
this->GetGradient(preds_, train_->labels, train_->group_index, grad_, hess_);
std::vector<unsigned> root_index;
base_gbm.DoBoost(grad_, hess_, train_->data, root_index);
// printf("xgboost_learner.h:UpdateOneIter\n");
// const unsigned ndata = static_cast<unsigned>(train_->Size());
// #pragma omp parallel for schedule( static )
// for (unsigned j = 0; j < ndata; ++j) {
// printf("haha:%d %f\n",j,base_gbm.Predict(train_->data, j, j));
// }
}
/*! \brief get intransformed prediction, without buffering */
inline void Predict(std::vector<float> &preds, const DMatrix &data) {
preds.resize(data.Size());
const unsigned ndata = static_cast<unsigned>(data.Size());
#pragma omp parallel for schedule( static )
#pragma omp parallel for schedule( static )
for (unsigned j = 0; j < ndata; ++j) {
preds[j] = base_gbm.Predict(data.data, j, -1);
}
preds[j] = base_gbm.Predict(data.data, j, -1);
}
}
public:
@@ -194,7 +201,7 @@ namespace xgboost {
inline void InteractPredict(std::vector<float> &preds, const DMatrix &data, unsigned buffer_offset) {
preds.resize(data.Size());
const unsigned ndata = static_cast<unsigned>(data.Size());
#pragma omp parallel for schedule( static )
#pragma omp parallel for schedule( static )
for (unsigned j = 0; j < ndata; ++j) {
preds[j] = base_gbm.InteractPredict(data.data, j, buffer_offset + j);
}
@@ -202,7 +209,7 @@ namespace xgboost {
/*! \brief repredict trial */
inline void InteractRePredict(const xgboost::base::DMatrix &data, unsigned buffer_offset) {
const unsigned ndata = static_cast<unsigned>(data.Size());
#pragma omp parallel for schedule( static )
#pragma omp parallel for schedule( static )
for (unsigned j = 0; j < ndata; ++j) {
base_gbm.InteractRePredict(data.data, j, buffer_offset + j);
}
@@ -212,10 +219,11 @@ namespace xgboost {
virtual inline void PredictBuffer(std::vector<float> &preds, const DMatrix &data, unsigned buffer_offset) {
preds.resize(data.Size());
const unsigned ndata = static_cast<unsigned>(data.Size());
#pragma omp parallel for schedule( static )
#pragma omp parallel for schedule( static )
for (unsigned j = 0; j < ndata; ++j) {
preds[j] = base_gbm.Predict(data.data, j, buffer_offset + j);
}
}
}
/*! \brief get the first order and second order gradient, given the transformed predictions and labels */
@@ -248,7 +256,7 @@ namespace xgboost {
* \param val value of the parameter
*/
inline void SetParam(const char *name, const char *val) {
if (!strcmp("loss_type", name)) loss_type = atoi(val);
if (!strcmp("loss_type", name)) loss_type = atoi(val);
if (!strcmp("bst:num_feature", name)) num_feature = atoi(val);
}