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

make xgcombine buffer work

Browse Source
This commit is contained in:
tqchen 2014-08-17 22:49:36 -07:00
parent 4ed4b08146
commit 0d9a8c042c
5 changed files with 205 additions and 207 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Makefile
View File

@ -1,6 +1,6 @@
export CC = clang export CC = gcc
export CXX = clang++ export CXX = g++
export CFLAGS = -Wall -O3 -msse2 -Wno-unknown-pragmas export CFLAGS = -Wall -O3 -msse2 -Wno-unknown-pragmas -fopenmp
# specify tensor path # specify tensor path
BIN = xgboost BIN = xgboost

2
python/xgboost_wrapper.cpp
View File

@ -140,7 +140,7 @@ extern "C"{
for (size_t i = 0; i < len; ++i) { for (size_t i = 0; i < len; ++i) {
const int ridx = idxset[i]; const int ridx = idxset[i];
SparseBatch::Inst inst = batch[ridx]; SparseBatch::Inst inst = batch[ridx];
utils::Check(ridx < batch.size, "slice index exceed number of rows"); utils::Check(static_cast<size_t>(ridx) < batch.size, "slice index exceed number of rows");
ret.row_data_.resize(ret.row_data_.size() + inst.length); ret.row_data_.resize(ret.row_data_.size() + inst.length);
memcpy(&ret.row_data_[ret.row_ptr_.back()], inst.data, memcpy(&ret.row_data_[ret.row_ptr_.back()], inst.data,
sizeof(SparseBatch::Entry) * inst.length); sizeof(SparseBatch::Entry) * inst.length);

2
src/learner/objective-inl.hpp
View File

@ -171,7 +171,7 @@ class SoftmaxMultiClassObj : public IObjFunction {
rec[k] = preds[j * nclass + k]; rec[k] = preds[j * nclass + k];
} }
Softmax(&rec); Softmax(&rec);
unsigned label = static_cast<unsigned>(info.labels[j]); int label = static_cast<int>(info.labels[j]);
utils::Check(label < nclass, "SoftmaxMultiClassObj: label exceed num_class"); utils::Check(label < nclass, "SoftmaxMultiClassObj: label exceed num_class");
const float wt = info.GetWeight(j); const float wt = info.GetWeight(j);
for (int k = 0; k < nclass; ++k) { for (int k = 0; k < nclass; ++k) {

1
tools/Makefile
View File

@ -12,7 +12,6 @@ export LDFLAGS= -pthread -lm
xgcombine_buffer : xgcombine_buffer.cpp xgcombine_buffer : xgcombine_buffer.cpp
$(BIN) : $(BIN) :
$(CXX) $(CFLAGS) $(LDFLAGS) -o $@ $(filter %.cpp %.o %.c, $^) $(CXX) $(CFLAGS) $(LDFLAGS) -o $@ $(filter %.cpp %.o %.c, $^)

401
tools/xgcombine_buffer.cpp
View File

@ -10,239 +10,238 @@
#include <cstring> #include <cstring>
#include <ctime> #include <ctime>
#include <cmath> #include <cmath>
#include "../regrank/xgboost_regrank_data.h" #include "../src/io/simple_dmatrix-inl.hpp"
#include "../utils/xgboost_utils.h" #include "../src/utils/utils.h"
using namespace xgboost; using namespace xgboost;
using namespace xgboost::booster; using namespace xgboost::io;
using namespace xgboost::regrank;
// header in dataset // header in dataset
struct Header{ struct Header{
FILE *fi; FILE *fi;
int tmp_num; int tmp_num;
int base; int base;
int num_feat; int num_feat;
// whether it's dense format // whether it's dense format
bool is_dense; bool is_dense;
bool warned; bool warned;
Header( void ){ this->warned = false; this->is_dense = false; } Header( void ){ this->warned = false; this->is_dense = false; }
inline void CheckBase( unsigned findex ){ inline void CheckBase( unsigned findex ){
if( findex >= (unsigned)num_feat && ! warned ) { if( findex >= (unsigned)num_feat && ! warned ) {
fprintf( stderr, "warning:some feature exceed bound, num_feat=%d\n", num_feat ); fprintf( stderr, "warning:some feature exceed bound, num_feat=%d\n", num_feat );
warned = true; warned = true;
} }
} }
}; };
inline int norm( std::vector<Header> &vec, int base = 0 ){ inline int norm( std::vector<Header> &vec, int base = 0 ){
int n = base; int n = base;
for( size_t i = 0; i < vec.size(); i ++ ){ for( size_t i = 0; i < vec.size(); i ++ ){
if( vec[i].is_dense ) vec[i].num_feat = 1; if( vec[i].is_dense ) vec[i].num_feat = 1;
vec[i].base = n; n += vec[i].num_feat; vec[i].base = n; n += vec[i].num_feat;
} }
return n; return n;
} }
inline void vclose( std::vector<Header> &vec ){ inline void vclose( std::vector<Header> &vec ){
for( size_t i = 0; i < vec.size(); i ++ ){ for( size_t i = 0; i < vec.size(); i ++ ){
fclose( vec[i].fi ); fclose( vec[i].fi );
} }
} }
inline int readnum( std::vector<Header> &vec ){ inline int readnum( std::vector<Header> &vec ){
int n = 0; int n = 0;
for( size_t i = 0; i < vec.size(); i ++ ){ for( size_t i = 0; i < vec.size(); i ++ ){
if( !vec[i].is_dense ){ if( !vec[i].is_dense ){
utils::Assert( fscanf( vec[i].fi, "%d", &vec[i].tmp_num ) == 1, "load num" ); utils::Assert( fscanf( vec[i].fi, "%d", &vec[i].tmp_num ) == 1, "load num" );
n += vec[i].tmp_num; n += vec[i].tmp_num;
}else{ }else{
n ++; n ++;
}
} }
return n; }
return n;
} }
inline void vskip( std::vector<Header> &vec ){ inline void vskip( std::vector<Header> &vec ){
for( size_t i = 0; i < vec.size(); i ++ ){ for( size_t i = 0; i < vec.size(); i ++ ){
if( !vec[i].is_dense ){ if( !vec[i].is_dense ){
utils::Assert( fscanf( vec[i].fi, "%*d%*[^\n]\n" ) >= 0 ); utils::Assert( fscanf( vec[i].fi, "%*d%*[^\n]\n" ) >= 0, "sparse" );
}else{ }else{
utils::Assert( fscanf( vec[i].fi, "%*f\n" ) >= 0 ); utils::Assert( fscanf( vec[i].fi, "%*f\n" ) >= 0, "dense" );
}
} }
}
} }
class DataLoader: public DMatrix{ class DataLoader: public DMatrixSimple {
public: public:
// whether to do node and edge feature renormalization // whether to do node and edge feature renormalization
int rescale; int rescale;
int linelimit; int linelimit;
public: public:
FILE *fp, *fwlist, *fgroup, *fweight; FILE *fp, *fwlist, *fgroup, *fweight;
std::vector<Header> fheader; std::vector<Header> fheader;
std::vector<FMatrixS::REntry> entry; DataLoader( void ){
DataLoader( void ){ rescale = 0;
rescale = 0; linelimit = -1;
linelimit = -1; fp = NULL; fwlist = NULL; fgroup = NULL; fweight = NULL;
fp = NULL; fwlist = NULL; fgroup = NULL; fweight = NULL; }
private:
inline void Load( std::vector<SparseBatch::Entry> &feats, std::vector<Header> &vec ){
SparseBatch::Entry e;
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", &e.findex, &e.fvalue ) == 2, "Error when load feat" );
vec[i].CheckBase( e.findex );
e.findex += vec[i].base;
feats.push_back(e);
}
}else{
utils::Assert( fscanf ( vec[i].fi, "%f", &e.fvalue ) == 1, "load feat" );
e.findex = vec[i].base;
feats.push_back(e);
}
} }
private: }
inline void Load( std::vector<unsigned> &findex, std::vector<float> &fvalue, std::vector<Header> &vec ){ inline void DoRescale( std::vector<SparseBatch::Entry> &vec ){
unsigned fidx; float fv; double sum = 0.0;
for( size_t i = 0; i < vec.size(); i ++ ){ for( size_t i = 0; i < vec.size(); i ++ ){
if( !vec[i].is_dense ) { sum += vec[i].fvalue * vec[i].fvalue;
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" ); sum = sqrt( sum );
vec[i].CheckBase( fidx ); for( size_t i = 0; i < vec.size(); i ++ ){
fidx += vec[i].base; vec[i].fvalue /= sum;
findex.push_back( fidx ); fvalue.push_back( fv ); }
} }
}else{ public:
utils::Assert( fscanf ( vec[i].fi, "%f", &fv ) == 1, "load feat" ); // basically we are loading all the data inside
fidx = vec[i].base; inline void Load( void ){
findex.push_back( fidx ); fvalue.push_back( fv ); this->Clear();
} float label, weight = 0.0f;
}
unsigned ngleft = 0, ngacc = 0;
if( fgroup != NULL ){
info.group_ptr.clear();
info.group_ptr.push_back(0);
} }
inline void DoRescale( std::vector<float> &vec ){
double sum = 0.0; while( fscanf( fp, "%f", &label ) == 1 ){
for( size_t i = 0; i < vec.size(); i ++ ){ if( ngleft == 0 && fgroup != NULL ){
sum += vec[i] * vec[i]; utils::Assert( fscanf( fgroup, "%u", &ngleft ) == 1, "group" );
} }
sum = sqrt( sum ); if( fweight != NULL ){
for( size_t i = 0; i < vec.size(); i ++ ){ utils::Assert( fscanf( fweight, "%f", &weight ) == 1, "weight" );
vec[i] /= sum; }
}
} ngleft -= 1; ngacc += 1;
public:
// basically we are loading all the data inside int pass = 1;
inline void Load( void ){ if( fwlist != NULL ){
this->data.Clear(); utils::Assert( fscanf( fwlist, "%u", &pass ) ==1, "pass" );
float label, weight = 0.0f; }
if( pass == 0 ){
unsigned ngleft = 0, ngacc = 0; vskip( fheader ); ngacc -= 1;
if( fgroup != NULL ){ }else{
info.group_ptr.clear(); const int nfeat = readnum( fheader );
info.group_ptr.push_back(0);
std::vector<SparseBatch::Entry> feats;
// pairs
this->Load( feats, fheader );
utils::Assert( feats.size() == (unsigned)nfeat, "nfeat" );
if( rescale != 0 ) this->DoRescale( feats );
// push back data :)
this->info.labels.push_back( label );
// push back weight if any
if( fweight != NULL ){
this->info.weights.push_back( weight );
} }
this->AddRow( feats );
while( fscanf( fp, "%f", &label ) == 1 ){ }
if( ngleft == 0 && fgroup != NULL ){ if( ngleft == 0 && fgroup != NULL && ngacc != 0 ){
utils::Assert( fscanf( fgroup, "%u", &ngleft ) == 1 ); info.group_ptr.push_back( info.group_ptr.back() + ngacc );
} utils::Assert( info.group_ptr.back() == info.num_row, "group size must match num rows" );
if( fweight != NULL ){ ngacc = 0;
utils::Assert( fscanf( fweight, "%f", &weight ) == 1 ); }
} // linelimit
if( linelimit >= 0 ) {
ngleft -= 1; ngacc += 1; if( -- linelimit <= 0 ) break;
}
int pass = 1;
if( fwlist != NULL ){
utils::Assert( fscanf( fwlist, "%u", &pass ) ==1 );
}
if( pass == 0 ){
vskip( fheader ); ngacc -= 1;
}else{
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 );
// push back weight if any
if( fweight != NULL ){
this->info.weights.push_back( weight );
}
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();
} }
if( ngleft == 0 && fgroup != NULL && ngacc != 0 ){
info.group_ptr.push_back( info.group_ptr.back() + ngacc );
utils::Assert( info.group_ptr.back() == info.num_row, "group size must match num rows" );
}
}
}; };
const char *folder = "features"; const char *folder = "features";
int main( int argc, char *argv[] ){ int main( int argc, char *argv[] ){
if( argc < 3 ){ if( argc < 3 ){
printf("Usage:xgcombine_buffer <inname> <outname> [options] -f [features] -fd [densefeatures]\n"\ printf("Usage:xgcombine_buffer <inname> <outname> [options] -f [features] -fd [densefeatures]\n" \
"options: -rescale -linelimit -fgroup <groupfilename> -wlist <whitelistinstance>\n"); "options: -rescale -linelimit -fgroup <groupfilename> -wlist <whitelistinstance>\n");
return 0; 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") ){
DataLoader loader; mode = 2; continue;
time_t start = time( NULL ); }
if( !strcmp( argv[i], "-rescale") ){
int mode = 0; loader.rescale = 1; continue;
for( int i = 3; i < argc; i ++ ){ }
if( !strcmp( argv[i], "-f") ){ if( !strcmp( argv[i], "-wlist") ){
mode = 0; continue; loader.fwlist = utils::FopenCheck( argv[ ++i ], "r" ); continue;
} }
if( !strcmp( argv[i], "-fd") ){ if( !strcmp( argv[i], "-fgroup") ){
mode = 2; continue; loader.fgroup = utils::FopenCheck( argv[ ++i ], "r" ); continue;
} }
if( !strcmp( argv[i], "-rescale") ){ if( !strcmp( argv[i], "-fweight") ){
loader.rescale = 1; continue; loader.fweight = utils::FopenCheck( argv[ ++i ], "r" ); continue;
} }
if( !strcmp( argv[i], "-wlist") ){ if( !strcmp( argv[i], "-linelimit") ){
loader.fwlist = utils::FopenCheck( argv[ ++i ], "r" ); continue; loader.linelimit = atoi( argv[ ++i ] ); continue;
}
if( !strcmp( argv[i], "-fgroup") ){
loader.fgroup = utils::FopenCheck( argv[ ++i ], "r" ); continue;
}
if( !strcmp( argv[i], "-fweight") ){
loader.fweight = 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 ) ); char name[ 256 ];
printf("start creating buffer...\n"); sprintf( name, "%s/%s.%s", folder, argv[1], argv[i] );
loader.Load(); Header h;
loader.SaveBinary( argv[2] ); h.fi = utils::FopenCheck( name, "r" );
// close files
fclose( loader.fp ); if( mode == 2 ){
if( loader.fwlist != NULL ) fclose( loader.fwlist ); h.is_dense = true; h.num_feat = 1;
if( loader.fgroup != NULL ) fclose( loader.fgroup ); loader.fheader.push_back( h );
vclose( loader.fheader ); }else{
printf("all generation end, %lu sec used\n", (unsigned long)(time(NULL) - start) ); utils::Assert( fscanf( h.fi, "%d", &h.num_feat ) == 1, "num feat" );
return 0; 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;
} }