1 files changed, 38 insertions, 26 deletions

diff --git a/dtrain/sample.h b/dtrain/sample.h
index b9bc4461..b6aa9abd 100644
--- a/dtrain/sample.h
+++ b/dtrain/sample.h
@@ -1,3 +1,7 @@
+#ifndef _DTRAIN_SAMPLE_H_
+#define _DTRAIN_SAMPLE_H_
+
+
 #include "kbestget.h"
 
 
@@ -7,9 +11,9 @@ namespace dtrain
 
 struct TPair
 {
-  double type;
-  SparseVector<double> first;
-  SparseVector<double> second;
+  SparseVector<double> first, second;
+  size_t first_rank, second_rank;
+  double first_score, second_score;
 };
 
 typedef vector<TPair> TrainingInstances;
@@ -18,35 +22,43 @@ typedef vector<TPair> TrainingInstances;
 void
 sample_all( KBestList* kb, TrainingInstances &training )
 {
-  double type;
   for ( size_t i = 0; i < kb->GetSize()-1; i++ ) {
-   for ( size_t j = i+1; j < kb->GetSize(); j++ ) {
-     if ( kb->scores[i] - kb->scores[j] < 0 ) {
-       type = -1; 
-     } else {
-       type = 1;
-     }
-     TPair p;
-     p.type = type;
-     p.first = kb->feats[i];
-     p.second = kb->feats[j];
-     training.push_back( p );
-   }
- }
-}
-
-/*void
-sample_all_only_neg(, vector<pair<SparSparseVector<double> > pairs)
-{
-
+    for ( size_t j = i+1; j < kb->GetSize(); j++ ) {
+      TPair p;
+      p.first = kb->feats[i];
+      p.second = kb->feats[j];
+      p.first_rank = i;
+      p.second_rank = j;
+      p.first_score = kb->scores[i];
+      p.second_score = kb->scores[j];
+      training.push_back( p );
+    }
+  }
 }
 
 void
-sample_random_pos()
+sample_all_rand( KBestList* kb, TrainingInstances &training )
 {
-  if ( rand() % 2 ) { // sample it?
-}*/
+  srand( time(NULL) );
+  for ( size_t i = 0; i < kb->GetSize()-1; i++ ) {
+    for ( size_t j = i+1; j < kb->GetSize(); j++ ) {
+      if ( rand() % 2 ) {
+      TPair p;
+      p.first = kb->feats[i];
+      p.second = kb->feats[j];
+      p.first_rank = i;
+      p.second_rank = j;
+      p.first_score = kb->scores[i];
+      p.second_score = kb->scores[j];
+      training.push_back( p );
+      }
+    }
+  }
+}
 
 
 } // namespace
 
+
+#endif
+