kbest, ksampler refactoring

1 files changed, 17 insertions, 31 deletions

diff --git a/dtrain/pairsampling.h b/dtrain/pairsampling.h
index a8521485..2e4ab155 100644
--- a/dtrain/pairsampling.h
+++ b/dtrain/pairsampling.h
@@ -8,47 +8,33 @@ namespace dtrain
 {
 
 
-struct Pair
-{
-  SparseVector<double> first,       second;
-  size_t               first_rank,  second_rank;
-  double               first_score, second_score;
-};
-
 inline void
-sample_all_pairs(Samples* kb, vector<Pair> &training)
+sample_all_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> > &training)
 {
-  for (size_t i = 0; i < kb->GetSize()-1; i++) {
-    for (size_t j = i+1; j < kb->GetSize(); j++) {
-      Pair 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];
+  for (size_t i = 0; i < s->size()-1; i++) {
+    for (size_t j = i+1; j < s->size(); j++) {
+      pair<ScoredHyp,ScoredHyp> p;
+      p.first = (*s)[i];
+      p.second = (*s)[j];
       training.push_back(p);
-    } // j
-  } // i
+    }
+  }
 }
 
 inline void
-sample_rand_pairs(Samples* kb, vector<Pair> &training, MT19937* prng)
+sample_rand_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> > &training,
+                  MT19937* prng)
 {
-  for (size_t i = 0; i < kb->GetSize()-1; i++) {
-    for (size_t j = i+1; j < kb->GetSize(); j++) {
+  for (size_t i = 0; i < s->size()-1; i++) {
+    for (size_t j = i+1; j < s->size(); j++) {
       if (prng->next() < .5) {
-        Pair 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];
+        pair<ScoredHyp,ScoredHyp> p;
+        p.first = (*s)[i];
+        p.second = (*s)[j];
         training.push_back(p);
       }
-    } // j
-  } // i
+    }
+  }
 }