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

make basic combine buf

Browse Source
This commit is contained in:
tqchen 2014-09-10 21:38:50 -07:00
parent fe9e89cadd
commit 87cc53f0cd
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
tools/xgcombine_buffer.cpp
View File

@ -11,6 +11,7 @@
#include <ctime> #include <ctime>
#include <cmath> #include <cmath>
#include "../src/io/simple_dmatrix-inl.hpp" #include "../src/io/simple_dmatrix-inl.hpp"
#include "../src/io/io.cpp"
#include "../src/utils/utils.h" #include "../src/utils/utils.h"
using namespace xgboost; using namespace xgboost;
@ -94,14 +95,14 @@ class DataLoader: public DMatrixSimple {
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 ) {
for( int j = 0; j < vec[i].tmp_num; j ++ ){ 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" ); utils::Assert( fscanf ( vec[i].fi, "%u:%f", &e.index, &e.fvalue ) == 2, "Error when load feat" );
vec[i].CheckBase( e.findex ); vec[i].CheckBase( e.index );
e.findex += vec[i].base; e.index += vec[i].base;
feats.push_back(e); feats.push_back(e);
} }
}else{ }else{
utils::Assert( fscanf ( vec[i].fi, "%f", &e.fvalue ) == 1, "load feat" ); utils::Assert( fscanf ( vec[i].fi, "%f", &e.fvalue ) == 1, "load feat" );
e.findex = vec[i].base; e.index = vec[i].base;
feats.push_back(e); feats.push_back(e);
} }
} }
@ -163,7 +164,7 @@ class DataLoader: public DMatrixSimple {
} }
if( ngleft == 0 && fgroup != NULL && ngacc != 0 ){ if( ngleft == 0 && fgroup != NULL && ngacc != 0 ){
info.group_ptr.push_back( info.group_ptr.back() + ngacc ); 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" ); utils::Assert( info.group_ptr.back() == info.num_row(), "group size must match num rows" );
ngacc = 0; ngacc = 0;
} }
// linelimit // linelimit
@ -173,7 +174,7 @@ class DataLoader: public DMatrixSimple {
} }
if( ngleft == 0 && fgroup != NULL && ngacc != 0 ){ if( ngleft == 0 && fgroup != NULL && ngacc != 0 ){
info.group_ptr.push_back( info.group_ptr.back() + ngacc ); 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" ); utils::Assert( info.group_ptr.back() == info.num_row(), "group size must match num rows" );
} }
} }
@ -236,7 +237,7 @@ int main( int argc, char *argv[] ){
printf("num_features=%d\n", norm( loader.fheader ) ); printf("num_features=%d\n", norm( loader.fheader ) );
printf("start creating buffer...\n"); printf("start creating buffer...\n");
loader.Load(); loader.Load();
loader.SaveBinary( argv[2] ); io::SaveDataMatrix(loader, argv[2]);
// close files // close files
fclose( loader.fp ); fclose( loader.fp );
if( loader.fwlist != NULL ) fclose( loader.fwlist ); if( loader.fwlist != NULL ) fclose( loader.fwlist );