begin refactoring

1 files changed, 64 insertions, 0 deletions

diff --git a/dtrain/pairsampling.h b/dtrain/pairsampling.h
new file mode 100644
index 00000000..502901af
--- /dev/null
+++ b/dtrain/pairsampling.h
@@ -0,0 +1,64 @@
+#ifndef _DTRAIN_SAMPLE_H_
+#define _DTRAIN_SAMPLE_H_
+
+
+#include "kbestget.h"
+
+
+namespace dtrain
+{
+
+
+struct TPair
+{
+  SparseVector<double> first, second;
+  size_t first_rank, second_rank;
+  double first_score, second_score;
+};
+
+typedef vector<TPair> TrainingInstances;
+
+
+void
+sample_all( KBestList* kb, TrainingInstances &training )
+{
+  for ( size_t i = 0; i < kb->GetSize()-1; i++ ) {
+    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_rand( KBestList* kb, TrainingInstances &training )
+{
+  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
+