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

rank pass toy

Browse Source
This commit is contained in:
kalenhaha 2014-04-07 23:25:35 +08:00
parent 40c380e40a
commit a10f594644
32 changed files with 2237 additions and 2146 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@ -12,6 +12,8 @@ export LDFLAGS= -pthread -lm
xgboost: regression/xgboost_reg_main.cpp regression/*.h booster/*.h booster/*/*.hpp booster/*.hpp
#xgboost: rank/xgboost_rank_main.cpp base/*.h rank/*.h booster/*.h booster/*/*.hpp booster/*.hpp
$(BIN) :
$(CXX) $(CFLAGS) $(LDFLAGS) -o $@ $(filter %.cpp %.o %.c, $^)

3
booster/xgboost_gbmbase.h
View File

@ -288,7 +288,8 @@ namespace xgboost{
booster_info.push_back(0);
this->ConfigBooster(boosters.back());
boosters.back()->InitModel();
}else{
}
else{
this->ConfigBooster(boosters.back());
}
return boosters.back();

13
demo/rank/README Normal file
View File

@ -0,0 +1,13 @@
Demonstrating how to use XGBoost accomplish regression tasks on computer hardware dataset https://archive.ics.uci.edu/ml/datasets/Computer+Hardware
Run: ./runexp.sh
Format of input: LIBSVM format
Format of ```featmap.txt: <featureid> <featurename> <q or i or int>\n ```:
- Feature id must be from 0 to number of features, in sorted order.
- i means this feature is binary indicator feature
- q means this feature is a quantitative value, such as age, time, can be missing
- int means this feature is integer value (when int is hinted, the decision boundary will be integer)
Explainations: https://github.com/tqchen/xgboost/wiki/Regression

16
demo/rank/runexp.sh Normal file
View File

@ -0,0 +1,16 @@
#!/bin/bash
# map the data to features. For convenience we only use 7 original attributes and encode them as features in a trivial way
python mapfeat.py
# split train and test
python mknfold.py machine.txt 1
# training and output the models
../../xgboost machine.conf
# output predictions of test data
../../xgboost machine.conf task=pred model_in=0002.model
# print the boosters of 0002.model in dump.raw.txt
../../xgboost machine.conf task=dump model_in=0002.model name_dump=dump.raw.txt
# print the boosters of 0002.model in dump.nice.txt with feature map
../../xgboost machine.conf task=dump model_in=0002.model fmap=featmap.txt name_dump=dump.nice.txt
# cat the result
cat dump.nice.txt

5
demo/rank/toy.eval Normal file
View File

@ -0,0 +1,5 @@
1 0:2 1:3 2:2
0 0:2 1:3 2:2
0 0:2 1:3 2:2
0 0:2 1:3 2:2
1 0:2 1:3 2:2

2
demo/rank/toy.eval.group Normal file
View File

@ -0,0 +1,2 @@
2
3

5
demo/rank/toy.test Normal file
View File

@ -0,0 +1,5 @@
1 0:2 1:3 2:2
0 0:2 1:3 2:2
0 0:2 1:3 2:2
0 0:2 1:3 2:2
1 0:2 1:3 2:2

2
demo/rank/toy.test.group Normal file
View File

@ -0,0 +1,2 @@
2
3

5
demo/rank/toy.train Normal file
View File

@ -0,0 +1,5 @@
1 0:2 1:3 2:2
0 0:2 1:3 2:2
0 0:2 1:3 2:2
0 0:2 1:3 2:2
1 0:2 1:3 2:2

2
demo/rank/toy.train.group Normal file
View File

@ -0,0 +1,2 @@
2
3

0
demo/rank/train Normal file
View File

9
dev/base/xgboost_boost_task.h
View File

@ -20,6 +20,7 @@ namespace xgboost{
class BoostTask{
public:
inline int Run(int argc, char *argv[]){
if (argc < 2){
printf("Usage: <config>\n");
return 0;
@ -34,6 +35,7 @@ namespace xgboost{
this->SetParam(name, val);
}
}
this->InitData();
this->InitLearner();
if (task == "dump"){
@ -128,6 +130,7 @@ namespace xgboost{
inline void InitData(void){
if (name_fmap != "NULL") fmap.LoadText(name_fmap.c_str());
if (task == "dump") return;
if (learning_task == RANKING){
@ -140,6 +143,7 @@ namespace xgboost{
// training
sscanf(train_path.c_str(), "%[^;];%s", instance_path, group_path);
data.CacheLoad(instance_path, group_path, silent != 0, use_buffer != 0);
utils::Assert(eval_data_names.size() == eval_data_paths.size());
for (size_t i = 0; i < eval_data_names.size(); ++i){
deval.push_back(new DMatrix());
@ -147,8 +151,6 @@ namespace xgboost{
deval.back()->CacheLoad(instance_path, group_path, silent != 0, use_buffer != 0);
}
}
}
else{
if (task == "pred" || task == "dumppath"){
@ -166,7 +168,9 @@ namespace xgboost{
}
learner_->SetData(&data, deval, eval_data_names);
if(!silent) printf("BoostTask:Data Initiation Done!\n");
}
inline void InitLearner(void){
cfg.BeforeFirst();
while (cfg.Next()){
@ -182,6 +186,7 @@ namespace xgboost{
learner_->InitModel();
}
learner_->InitTrainer();
if(!silent) printf("BoostTask:InitLearner Done!\n");
}
inline void TaskTrain(void){

67
dev/base/xgboost_data_instance.h
View File

@ -70,17 +70,27 @@ namespace xgboost{
(unsigned)data.NumRow(), (unsigned)data.NumCol(), (unsigned long)data.NumEntry(), fname);
}
fclose(file);
LoadGroup(fgroup,silent);
}
inline void LoadGroup(const char* fgroup, bool silent = false){
//if exists group data load it in
FILE *file_group = fopen64(fgroup, "r");
if (file_group != NULL){
group_index.push_back(0);
int tmp = 0, acc = 0;
while (fscanf(file_group, "%d", tmp) == 1){
int tmp = 0, acc = 0,cnt = 0;
while (fscanf(file_group, "%d", &tmp) == 1){
acc += tmp;
group_index.push_back(acc);
cnt++;
}
if(!silent) printf("%d groups are loaded from %s\n",cnt,fgroup);
fclose(file_group);
}else{
if(!silent) printf("There is no group file\n");
}
}
/*!
* \brief load from binary file
@ -100,24 +110,11 @@ namespace xgboost{
data.InitData();
if (!silent){
printf("%ux%u matrix with %lu entries is loaded from %s\n",
printf("%ux%u matrix with %lu entries is loaded from %s as binary\n",
(unsigned)data.NumRow(), (unsigned)data.NumCol(), (unsigned long)data.NumEntry(), fname);
}
//if group data exists load it in
FILE *file_group = fopen64(fgroup, "r");
if (file_group != NULL){
int group_index_size = 0;
utils::FileStream group_stream(file_group);
utils::Assert(group_stream.Read(&group_index_size, sizeof(int)) != 0, "Load group indice size");
group_index.resize(group_index_size);
utils::Assert(group_stream.Read(&group_index, sizeof(int)* group_index_size) != 0, "Load group indice");
if (!silent){
printf("the group index of %d groups is loaded from %s\n",
group_index_size - 1, fgroup);
}
}
LoadGroupBinary(fgroup,silent);
return true;
}
/*!
@ -134,16 +131,42 @@ namespace xgboost{
fs.Write(&labels[0], sizeof(float)* data.NumRow());
fs.Close();
if (!silent){
printf("%ux%u matrix with %lu entries is saved to %s\n",
printf("%ux%u matrix with %lu entries is saved to %s as binary\n",
(unsigned)data.NumRow(), (unsigned)data.NumCol(), (unsigned long)data.NumEntry(), fname);
}
SaveGroupBinary(fgroup,silent);
}
inline void SaveGroupBinary(const char* fgroup, bool silent = false){
//save group data
if (group_index.size() > 0){
utils::FileStream file_group(utils::FopenCheck(fgroup, "wb"));
int group_index_size = group_index.size();
file_group.Write(&(group_index_size), sizeof(int));
file_group.Write(&group_index[0], sizeof(int) * group_index_size);
file_group.Close();
if(!silent){printf("Index info of %d groups is saved to %s as binary\n",group_index_size-1,fgroup);}
}
}
inline void LoadGroupBinary(const char* fgroup, bool silent = false){
//if group data exists load it in
FILE *file_group = fopen64(fgroup, "r");
if (file_group != NULL){
int group_index_size = 0;
utils::FileStream group_stream(file_group);
utils::Assert(group_stream.Read(&group_index_size, sizeof(int)) != 0, "Load group indice size");
group_index.resize(group_index_size);
utils::Assert(group_stream.Read(&group_index[0], sizeof(int) * group_index_size) != 0, "Load group indice");
if (!silent){
printf("Index info of %d groups is loaded from %s as binary\n",
group_index.size() - 1, fgroup);
}
fclose(file_group);
}else{
if(!silent){printf("The binary file of group info not exists");}
}
}
@ -161,11 +184,13 @@ namespace xgboost{
if (len > 8 && !strcmp(fname + len - 7, ".buffer")){
this->LoadBinary(fname, fgroup, silent); return;
}
char bname[1024];
char bname[1024],bgroup[1024];
sprintf(bname, "%s.buffer", fname);
if (!this->LoadBinary(bname, fgroup, silent)){
sprintf(bgroup, "%s.buffer", fgroup);
if (!this->LoadBinary(bname, bgroup, silent))
{
this->LoadText(fname, fgroup, silent);
if (savebuffer) this->SaveBinary(bname, fgroup, silent);
if (savebuffer) this->SaveBinary(bname, bgroup, silent);
}
}
private:

2
dev/base/xgboost_learner.h
View File

@ -96,6 +96,7 @@ namespace xgboost {
*/
inline void InitModel(void) {
base_gbm.InitModel();
if(!silent) printf("BoostLearner:InitModel Done!\n");
}
/*!
* \brief load model from stream
@ -210,7 +211,6 @@ namespace xgboost {
/*! \brief get intransformed predictions, given data */
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 )
for (unsigned j = 0; j < ndata; ++j) {

19
dev/rank/xgboost_rank_main.cpp
View File

@ -11,20 +11,11 @@
#include "../base/xgboost_boost_task.h"
#include "xgboost_rank.h"
#include "../regression/xgboost_reg.h"
#include "../regression/xgboost_reg_main.cpp"
#include "../base/xgboost_data_instance.h"
int main(int argc, char *argv[]) {
xgboost::random::Seed(0);
xgboost::base::BoostTask tsk;
xgboost::utils::ConfigIterator itr(argv[1]);
/* int learner_index = 0;
while (itr.Next()){
if (!strcmp(itr.name(), "learning_task")){
learner_index = atoi(itr.val());
}
}*/
xgboost::rank::RankBoostLearner* rank_learner = new xgboost::rank::RankBoostLearner;
xgboost::base::BoostLearner *parent = static_cast<xgboost::base::BoostLearner*>(rank_learner);
tsk.SetLearner(parent);
return tsk.Run(argc, argv);
xgboost::base::BoostTask rank_tsk;
rank_tsk.SetLearner(new xgboost::rank::RankBoostLearner);
return rank_tsk.Run(argc, argv);
}

1
dev/rank/xgboost_sample.h
View File

@ -115,6 +115,7 @@ namespace xgboost {
Pairs GenPairs(const std::vector<float> &preds,
const std::vector<float> &labels,
int start, int end){
utils::Assert(sampler_ != NULL,"Not config the sampler yet. Add rank:sampler in the config file\n");
return sampler_->GenPairs(preds, labels, start, end);
}
private:

3
regression/xgboost_reg.h
View File

@ -94,7 +94,8 @@ namespace xgboost{
base_gbm.InitTrainer();
if (mparam.loss_type == kLogisticClassify){
evaluator_.AddEval("error");
}else{
}
else{
evaluator_.AddEval("rmse");
}
evaluator_.Init();

3
regression/xgboost_reg_data.h
View File

@ -52,7 +52,8 @@ namespace xgboost{
unsigned index; float value;
if (sscanf(tmp, "%u:%f", &index, &value) == 2){
findex.push_back(index); fvalue.push_back(value);
}else{
}
else{
if (!init){
labels.push_back(label);
data.AddRow(findex, fvalue);

3
regression/xgboost_reg_eval.h
View File

@ -55,7 +55,8 @@ namespace xgboost{
for (unsigned i = 0; i < ndata; ++i){
if (preds[i] > 0.5f){
if (labels[i] < 0.5f) nerr += 1;
}else{
}
else{
if (labels[i] > 0.5f) nerr += 1;
}
}

25
regression/xgboost_reg_main.cpp
View File

@ -50,7 +50,8 @@ namespace xgboost{
}
if (task == "pred"){
this->TaskPred();
}else{
}
else{
this->TaskTrain();
}
return 0;
@ -113,7 +114,8 @@ namespace xgboost{
if (task == "dump") return;
if (task == "pred" || task == "dumppath"){
data.CacheLoad(test_path.c_str(), silent != 0, use_buffer != 0);
}else{
}
else{
// training
data.CacheLoad(train_path.c_str(), silent != 0, use_buffer != 0);
utils::Assert(eval_data_names.size() == eval_data_paths.size());
@ -133,7 +135,8 @@ namespace xgboost{
utils::FileStream fi(utils::FopenCheck(model_in.c_str(), "rb"));
learner.LoadModel(fi);
fi.Close();
}else{
}
else{
utils::Assert(task == "train", "model_in not specified");
learner.InitModel();
}
@ -156,7 +159,8 @@ namespace xgboost{
if (save_period == 0 || num_round % save_period != 0){
if (model_out == "NULL"){
this->SaveModel(num_round - 1);
}else{
}
else{
this->SaveModel(model_out.c_str());
}
}
@ -177,7 +181,8 @@ namespace xgboost{
if (!strcmp(cfg_batch.name(), "run")){
learner.UpdateInteract(interact_action);
batch_action += 1;
} else{
}
else{
learner.SetParam(cfg_batch.name(), cfg_batch.val());
}
}
@ -273,8 +278,8 @@ namespace xgboost{
};
};
int main( int argc, char *argv[] ){
xgboost::random::Seed( 0 );
xgboost::regression::RegBoostTask tsk;
return tsk.Run( argc, argv );
}
// int main( int argc, char *argv[] ){
// xgboost::random::Seed( 0 );
// xgboost::regression::RegBoostTask tsk;
// return tsk.Run( argc, argv );
// }

15
utils/xgboost_config.h
View File

@ -94,7 +94,8 @@ namespace xgboost{
case '\"':
if (i == 0){
ParseStr(tok); ch_buf = fgetc(fi); return new_line;
}else{
}
else{
Error("token followed directly by string");
}
case '=':
@ -102,7 +103,8 @@ namespace xgboost{
ch_buf = fgetc(fi);
tok[0] = '=';
tok[1] = '\0';
}else{
}
else{
tok[i] = '\0';
}
return new_line;
@ -155,7 +157,8 @@ namespace xgboost{
if (priority == 0){
names.push_back(std::string(name));
values.push_back(std::string(val));
}else{
}
else{
names_high.push_back(std::string(name));
values_high.push_back(std::string(val));
}
@ -184,7 +187,8 @@ namespace xgboost{
size_t i = idx - 1;
if (i >= names.size()){
return names_high[i - names.size()].c_str();
}else{
}
else{
return names[i].c_str();
}
}
@ -197,7 +201,8 @@ namespace xgboost{
size_t i = idx - 1;
if (i >= values.size()){
return values_high[i - values.size()].c_str();
}else{
}
else{
return values[i].c_str();
}
}

6
utils/xgboost_matrix_csr.h
View File

@ -50,7 +50,8 @@ namespace xgboost{
if (!UseAcList){
rptr.clear();
rptr.resize(nrows + 1, 0);
}else{
}
else{
Assert(nrows + 1 == rptr.size(), "rptr must be initialized already");
this->Cleanup();
}
@ -79,7 +80,8 @@ namespace xgboost{
rptr[i] = start;
start += rlen;
}
}else{
}
else{
// case with active list
std::sort(aclist.begin(), aclist.end());

2
utils/xgboost_omp.h
View File

@ -10,7 +10,7 @@
#if defined(_OPENMP)
#include <omp.h>
#else
//#warning "OpenMP is not available, compile to single thread code"
#warning "OpenMP is not available, compile to single thread code"
inline int omp_get_thread_num() { return 0; }
inline int omp_get_num_threads() { return 1; }
inline void omp_set_num_threads(int nthread) {}

3
utils/xgboost_random.h
View File

@ -88,7 +88,8 @@ namespace xgboost{
u = NextDouble();
} while (u == 0.0);
return SampleGamma(alpha + 1.0, beta) * pow(u, 1.0 / alpha);
} else {
}
else {
double d, c, x, v, u;
d = alpha - 1.0 / 3.0;
c = 1.0 / sqrt(9.0 * d);