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

add new combine tool as promised

Browse Source
This commit is contained in:
tqchen 2014-05-02 12:55:34 -07:00
parent 657c617215
commit 3128e718e2
3 changed files with 286 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
regrank/xgboost_regrank_data.h
View File

@ -15,6 +15,8 @@
*/
#include <cstdio>
#include <vector>
#include <string>
#include <cstring>
#include "../booster/xgboost_data.h"
#include "../utils/xgboost_utils.h"
#include "../utils/xgboost_stream.h"
@ -106,6 +108,13 @@ namespace xgboost{
data.LoadBinary(fs);
info.labels.resize(data.NumRow());
utils::Assert(fs.Read(&info.labels[0], sizeof(float)* data.NumRow()) != 0, "DMatrix LoadBinary");
{// load in group ptr
unsigned ngptr;
if( fs.Read(&ngptr, sizeof(unsigned) ) != 0 ){
info.group_ptr.resize( ngptr );
utils::Assert( fs.Read(&info.group_ptr[0], sizeof(unsigned) * ngptr) != 0, "Load group file");
}
}
fs.Close();
// initialize column support as well
data.InitData();
@ -113,8 +122,10 @@ namespace xgboost{
if (!silent){
printf("%ux%u matrix with %lu entries is loaded from %s\n",
(unsigned)data.NumRow(), (unsigned)data.NumCol(), (unsigned long)data.NumEntry(), fname);
if( info.group_ptr.size() != 0 ){
printf("data contains %u groups\n", (unsigned)info.group_ptr.size() );
}
}
this->TryLoadGroup(fname, silent);
this->TryLoadWeight(fname, silent);
return true;
}
@ -129,11 +140,20 @@ namespace xgboost{
utils::FileStream fs(utils::FopenCheck(fname, "wb"));
data.SaveBinary(fs);
utils::Assert( info.labels.size() == data.NumRow(), "label size is not consistent with feature matrix size" );
fs.Write(&info.labels[0], sizeof(float) * data.NumRow());
{// write out group ptr
unsigned ngptr = static_cast<unsigned>( info.group_ptr.size() );
fs.Write(&ngptr, sizeof(unsigned) );
fs.Write(&info.group_ptr[0], sizeof(unsigned) * ngptr);
}
fs.Close();
if (!silent){
printf("%ux%u matrix with %lu entries is saved to %s\n",
(unsigned)data.NumRow(), (unsigned)data.NumCol(), (unsigned long)data.NumEntry(), fname);
if( info.group_ptr.size() != 0 ){
printf("data contains %u groups\n", (unsigned)info.group_ptr.size() );
}
}
}
/*!

26
tools/Makefile Normal file
View File

@ -0,0 +1,26 @@
export CC = gcc
export CXX = g++
export CFLAGS = -Wall -O3 -msse2 -Wno-unknown-pragmas -fopenmp
# specify tensor path
BIN = xgcombine_buffer
OBJ =
.PHONY: clean all
all: $(BIN) $(OBJ)
export LDFLAGS= -pthread -lm
xgcombine_buffer : xgcombine_buffer.cpp
$(BIN) :
$(CXX) $(CFLAGS) $(LDFLAGS) -o $@ $(filter %.cpp %.o %.c, $^)
$(OBJ) :
$(CXX) -c $(CFLAGS) -o $@ $(firstword $(filter %.cpp %.c, $^) )
install:
cp -f -r $(BIN) $(INSTALL_PATH)
clean:
$(RM) $(OBJ) $(BIN) *~

238
tools/xgcombine_buffer.cpp Normal file
View File

@ -0,0 +1,238 @@
/*!
* a tool to combine different set of features into binary buffer
* not well organized code, but does it's job
* \author Tianqi Chen: tianqi.tchen@gmail.com
*/
#define _CRT_SECURE_NO_WARNINGS
#define _CRT_SECURE_NO_DEPRECATE
#include <cstdio>
#include <cstring>
#include <ctime>
#include <cmath>
#include "../regrank/xgboost_regrank_data.h"
#include "../utils/xgboost_utils.h"
using namespace xgboost;
using namespace xgboost::booster;
using namespace xgboost::regrank;
// header in dataset
struct Header{
FILE *fi;
int tmp_num;
int base;
int num_feat;
// whether it's dense format
bool is_dense;
bool warned;
Header( void ){ this->warned = false; this->is_dense = false; }
inline void CheckBase( unsigned findex ){
if( findex >= (unsigned)num_feat && ! warned ) {
fprintf( stderr, "warning:some feature exceed bound, num_feat=%d\n", num_feat );
warned = true;
}
}
};
inline int norm( std::vector<Header> &vec, int base = 0 ){
int n = base;
for( size_t i = 0; i < vec.size(); i ++ ){
if( vec[i].is_dense ) vec[i].num_feat = 1;
vec[i].base = n; n += vec[i].num_feat;
}
return n;
}
inline void vclose( std::vector<Header> &vec ){
for( size_t i = 0; i < vec.size(); i ++ ){
fclose( vec[i].fi );
}
}
inline int readnum( std::vector<Header> &vec ){
int n = 0;
for( size_t i = 0; i < vec.size(); i ++ ){
if( !vec[i].is_dense ){
utils::Assert( fscanf( vec[i].fi, "%d", &vec[i].tmp_num ) == 1, "load num" );
n += vec[i].tmp_num;
}else{
n ++;
}
}
return n;
}
inline void vskip( std::vector<Header> &vec ){
for( size_t i = 0; i < vec.size(); i ++ ){
if( !vec[i].is_dense ){
utils::Assert( fscanf( vec[i].fi, "%*d%*[^\n]\n" ) >= 0 );
}else{
utils::Assert( fscanf( vec[i].fi, "%*f\n" ) >= 0 );
}
}
}
class DataLoader: public DMatrix{
public:
// whether to do node and edge feature renormalization
int rescale;
int linelimit;
public:
FILE *fp, *fwlist, *fgroup;
std::vector<Header> fheader;
std::vector<FMatrixS::REntry> entry;
DataLoader( void ){
rescale = 0;
linelimit = -1;
fp = NULL; fwlist = NULL; fgroup = NULL;
}
private:
inline void Load( std::vector<unsigned> &findex, std::vector<float> &fvalue, std::vector<Header> &vec ){
unsigned fidx; float fv;
for( size_t i = 0; i < vec.size(); i ++ ){
if( !vec[i].is_dense ) {
for( int j = 0; j < vec[i].tmp_num; j ++ ){
utils::Assert( fscanf ( vec[i].fi, "%u:%f", &fidx, &fv ) == 2, "Error when load feat" );
vec[i].CheckBase( fidx );
fidx += vec[i].base;
findex.push_back( fidx ); fvalue.push_back( fv );
}
}else{
utils::Assert( fscanf ( vec[i].fi, "%f", &fv ) == 1, "load feat" );
fidx = vec[i].base;
findex.push_back( fidx ); fvalue.push_back( fv );
}
}
}
inline void DoRescale( std::vector<float> &vec ){
double sum = 0.0;
for( size_t i = 0; i < vec.size(); i ++ ){
sum += vec[i] * vec[i];
}
sum = sqrt( sum );
for( size_t i = 0; i < vec.size(); i ++ ){
vec[i] /= sum;
}
}
public:
// basically we are loading all the data inside
inline void Load( void ){
this->data.Clear();
float label;
unsigned ngleft = 0, ngacc = 0;
if( fgroup != NULL ){
info.group_ptr.clear();
info.group_ptr.push_back(0);
}
while( fscanf( fp, "%f", &label ) == 1 ){
if( ngleft == 0 && fgroup != NULL ){
utils::Assert( fscanf( fgroup, "%u", &ngleft ) == 1 );
}
ngleft -= 1; ngacc += 1;
if( fwlist != NULL ){
int pass;
utils::Assert( fscanf( fwlist, "%u", &pass ) ==1 );
if( pass == 0 ){
vskip( fheader ); ngacc -= 1;
}
}
const int nfeat = readnum( fheader );
std::vector<unsigned> findex;
std::vector<float> fvalue;
// pairs
this->Load( findex, fvalue, fheader );
utils::Assert( findex.size() == (unsigned)nfeat );
if( rescale != 0 ) this->DoRescale( fvalue );
// push back data :)
this->info.labels.push_back( label );
this->data.AddRow( findex, fvalue );
if( ngleft == 0 && fgroup != NULL && ngacc != 0 ){
info.group_ptr.push_back( info.group_ptr.back() + ngacc );
utils::Assert( info.group_ptr.back() == data.NumRow(), "group size must match num rows" );
ngacc = 0;
}
// linelimit
if( linelimit >= 0 ) {
if( -- linelimit <= 0 ) break;
}
}
if( ngleft == 0 && fgroup != NULL && ngacc != 0 ){
info.group_ptr.push_back( info.group_ptr.back() + ngacc );
utils::Assert( info.group_ptr.back() == data.NumRow(), "group size must match num rows" );
}
this->data.InitData();
}
};
const char *folder = "features";
int main( int argc, char *argv[] ){
if( argc < 3 ){
printf("Usage:xgcombine_buffer <inname> <outname> [options] -f [features] -fd [densefeatures]\n"\
"options: -rescale -linelimit -fgroup <groupfilename> -wlist <whitelistinstance>\n");
return 0;
}
DataLoader loader;
time_t start = time( NULL );
int mode = 0;
for( int i = 3; i < argc; i ++ ){
if( !strcmp( argv[i], "-f") ){
mode = 0; continue;
}
if( !strcmp( argv[i], "-fd") ){
mode = 2; continue;
}
if( !strcmp( argv[i], "-rescale") ){
loader.rescale = 1; continue;
}
if( !strcmp( argv[i], "-wlist") ){
loader.fwlist = utils::FopenCheck( argv[ ++i ], "r" ); continue;
}
if( !strcmp( argv[i], "-fgroup") ){
loader.fgroup = utils::FopenCheck( argv[ ++i ], "r" ); continue;
}
if( !strcmp( argv[i], "-linelimit") ){
loader.linelimit = atoi( argv[ ++i ] ); continue;
}
char name[ 256 ];
sprintf( name, "%s/%s.%s", folder, argv[1], argv[i] );
Header h;
h.fi = utils::FopenCheck( name, "r" );
if( mode == 2 ){
h.is_dense = true; h.num_feat = 1;
loader.fheader.push_back( h );
}else{
utils::Assert( fscanf( h.fi, "%d", &h.num_feat ) == 1, "num feat" );
switch( mode ){
case 0: loader.fheader.push_back( h ); break;
default: ;
}
}
}
loader.fp = utils::FopenCheck( argv[1], "r" );
printf("num_features=%d\n", norm( loader.fheader ) );
printf("start creating buffer...\n");
loader.Load();
loader.SaveBinary( argv[2] );
// close files
fclose( loader.fp );
if( loader.fwlist != NULL ) fclose( loader.fwlist );
if( loader.fgroup != NULL ) fclose( loader.fgroup );
vclose( loader.fheader );
printf("all generation end, %lu sec used\n", (unsigned long)(time(NULL) - start) );
return 0;
}