added basic multipartite pair sampling

4 files changed, 42 insertions, 10 deletions

diff --git a/dtrain/dtrain.cc b/dtrain/dtrain.cc
index 37430fb9..9b1bbe68 100644
--- a/dtrain/dtrain.cc
+++ b/dtrain/dtrain.cc
@@ -297,6 +297,8 @@ main(int argc, char** argv)
         sample_all_pairs(samples, pairs);
       if (pair_sampling == "rand")
         sample_rand_pairs(samples, pairs, &rng);
+      if (pair_sampling == "108010")
+        sample108010(samples, pairs);
        
       for (vector<pair<ScoredHyp,ScoredHyp> >::iterator ti = pairs.begin();
             ti != pairs.end(); ti++) {
diff --git a/dtrain/pairsampling.h b/dtrain/pairsampling.h
index 6db0c045..131e90ca 100644
--- a/dtrain/pairsampling.h
+++ b/dtrain/pairsampling.h
@@ -1,13 +1,12 @@
 #ifndef _DTRAIN_PAIRSAMPLING_H_
 #define _DTRAIN_PAIRSAMPLING_H_
 
-
 namespace dtrain
 {
 
 
 inline void
-sample_all_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> > &training)
+sample_all_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training)
 {
   for (unsigned i = 0; i < s->size()-1; i++) {
     for (unsigned j = i+1; j < s->size(); j++) {
@@ -20,7 +19,7 @@ sample_all_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> > &train
 }
 
 inline void
-sample_rand_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> > &training,
+sample_rand_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training,
                   MT19937* prng)
 {
   for (unsigned i = 0; i < s->size()-1; i++) {
@@ -35,6 +34,37 @@ sample_rand_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> > &trai
   }
 }
 
+bool
+sort_samples_by_score(ScoredHyp a, ScoredHyp b)
+{
+  return a.score < b.score;
+}
+
+inline void
+sample108010(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training)
+{
+  sort(s->begin(), s->end(), sort_samples_by_score);
+  pair<ScoredHyp,ScoredHyp>  p;
+  unsigned sz = s->size();
+  unsigned slice = 10;
+  unsigned sep = sz%slice;
+  if (sep == 0) sep = sz/slice;
+  for (unsigned i = 0; i < sep; i++) {
+    for(unsigned j = sep; j < sz; j++) {
+      p.first = (*s)[i];
+      p.second = (*s)[j];
+      if(p.first.rank < p.second.rank) training.push_back(p);
+    }
+  }
+  for (unsigned i = sep; i < sz-sep; i++) {
+    for (unsigned j = sz-sep; j < sz; j++) {
+      p.first = (*s)[i];
+      p.second = (*s)[j];
+      if(p.first.rank < p.second.rank) training.push_back(p);
+    }
+  }
+}
+
 
 } // namespace
 
diff --git a/dtrain/test/example/dtrain.ini b/dtrain/test/example/dtrain.ini
index b1b9b7bd..068074c4 100644
--- a/dtrain/test/example/dtrain.ini
+++ b/dtrain/test/example/dtrain.ini
@@ -1,12 +1,12 @@
 decoder_config=test/example/cdec.ini
 k=100
-N=4
-epochs=2
+N=3
+epochs=3
 input=test/example/nc-1k.gz
 scorer=stupid_bleu
-output=- #test/example/weights.gz
-stop_after=2
-sample_from=forest
-pair_sampling=rand
+output=/tmp/weights.gz
+stop_after=1000
+sample_from=kbest
+pair_sampling=all
 print_weights=Glue WordPenalty LanguageModel LanguageModel_OOV PhraseModel_0 PhraseModel_1 PhraseModel_2 PhraseModel_3 PhraseModel_4 PassThrough
-tmp=./
+tmp=/tmp
diff --git a/dtrain/test/example/weights.gz b/dtrain/test/example/weights.gz
deleted file mode 100644
index 7960a05a..00000000
--- a/dtrain/test/example/weights.gz
+++ /dev/null