From f3c98d0c4b04d347e344df670b29fa5307aea015 Mon Sep 17 00:00:00 2001
From: tqchen <workcrow@gmail.com>
Date: Sat, 1 Mar 2014 21:15:54 -0800
Subject: [PATCH] add smart load

---
 regression/xgboost_reg_main.cpp | 10 +++++++---
 regression/xgboost_regdata.h    | 17 +++++++++++------
 2 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/regression/xgboost_reg_main.cpp b/regression/xgboost_reg_main.cpp
index 61751b961..298f22530 100644
--- a/regression/xgboost_reg_main.cpp
+++ b/regression/xgboost_reg_main.cpp
@@ -51,6 +51,7 @@ namespace xgboost{
             }
             inline void SetParam( const char *name, const char *val ){
                 if( !strcmp("silent", name ) )       silent = atoi( val );
+                if( !strcmp("use_buffer", name ) )   use_buffer = atoi( val );
                 if( !strcmp("seed", name ) )         random::Seed( atoi(val) );
                 if( !strcmp("num_round", name ) )    num_round = atoi( val );
                 if( !strcmp("save_period", name ) )  save_period = atoi( val );
@@ -71,6 +72,7 @@ namespace xgboost{
             RegBoostTask( void ){
                 // default parameters
                 silent = 0;
+                use_buffer = 1;
                 num_round = 10;
                 save_period = 0;
                 task = "train";                
@@ -89,14 +91,14 @@ namespace xgboost{
             inline void InitData( void ){
                 if( task == "dump") return;
                 if( task == "test" || task == "dumppath" ){
-                    data.CacheLoad( test_path.c_str() );
+                    data.CacheLoad( test_path.c_str(), silent!=0, use_buffer!=0 );
                 }else{
                     // training 
-                    data.CacheLoad( train_path.c_str() );
+                    data.CacheLoad( train_path.c_str(), 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() );
-                        deval.back()->CacheLoad( eval_data_paths[i].c_str() );
+                        deval.back()->CacheLoad( eval_data_paths[i].c_str(), silent!=0, use_buffer!=0 );
                     }
                 }
                 learner.SetData( &data, deval, eval_data_names );
@@ -169,6 +171,8 @@ namespace xgboost{
         private:
             /* \brief whether silent */
             int silent;
+            /* \brief whether use auto binary buffer */
+            int use_buffer;
             /* \brief number of boosting iterations */
             int num_round;            
             /* \brief the period to save the model, 0 means only save the final round model */
diff --git a/regression/xgboost_regdata.h b/regression/xgboost_regdata.h
index 56c1bef47..2ef822f45 100644
--- a/regression/xgboost_regdata.h
+++ b/regression/xgboost_regdata.h
@@ -116,20 +116,25 @@ namespace xgboost{
                 }
             }
             /*! 
-            * \brief cache load data given a file name, the function will first check if fname + '.xgbuffer' 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,
             *        if binary buffer exists, it will reads from binary buffer, otherwise, it will load from text file,
             *        and try to create a buffer file 
             * \param fname name of binary data
             * \param silent whether print information or not
-            * \return whether loading is success
-            */            
-            inline void CacheLoad( const char *fname, bool silent = false ){
+            * \param savebuffer whether do save binary buffer if it is text
+            */
+            inline void CacheLoad( const char *fname, bool silent = false, bool savebuffer = true ){
+                int len = strlen( fname );
+                if( len > 8 && !strcmp( fname + len - 7,  ".buffer") ){
+                    this->LoadBinary( fname, silent ); return;
+                }
                 char bname[ 1024 ];
                 sprintf( bname, "%s.buffer", fname );
                 if( !this->LoadBinary( bname, silent ) ){
                     this->LoadText( fname, silent );
-                    this->SaveBinary( bname, silent );
-                }                
+                    if( savebuffer ) this->SaveBinary( bname, silent );
+                }
             }
         private:
             /*! \brief update num_feature info */