kbest repo

3 files changed, 61 insertions, 0 deletions

diff --git a/mteval/ns.h b/mteval/ns.h
index 4e4c6975..ac7b0a23 100644
--- a/mteval/ns.h
+++ b/mteval/ns.h
@@ -56,6 +56,11 @@ class SufficientStats {
   }
   void Encode(std::string* out) const;
 
+  void swap(SufficientStats& other) {
+    id_.swap(other.id_);
+    fields.swap(other.fields);
+  }
+
   std::string id_;
   std::vector<float> fields;
 };
diff --git a/training/kbest_repository.cc b/training/kbest_repository.cc
new file mode 100644
index 00000000..145b40a2
--- /dev/null
+++ b/training/kbest_repository.cc
@@ -0,0 +1,37 @@
+#include "kbest_repository.h"
+
+#include <boost/functional/hash.hpp>
+
+using namespace std;
+
+struct ApproxVectorHasher {
+  static const size_t MASK = 0xFFFFFFFFull;
+  union UType {
+    double f;   // leave as double
+    size_t i;
+  };
+  static inline double round(const double x) {
+    UType t;
+    t.f = x;
+    size_t r = t.i & MASK;
+    if ((r << 1) > MASK)
+      t.i += MASK - r + 1;
+    else
+      t.i &= (1ull - MASK);
+    return t.f;
+  }
+  size_t operator()(const SparseVector<double>& x) const {
+    size_t h = 0x573915839;
+    for (SparseVector<double>::const_iterator it = x.begin(); it != x.end(); ++it) {
+      UType t;
+      t.f = it->second;
+      if (t.f) {
+        size_t z = (t.i >> 32);
+        boost::hash_combine(h, it->first);
+        boost::hash_combine(h, z);
+      }
+    }
+    return h;
+  }
+};
+
diff --git a/training/kbest_repository.h b/training/kbest_repository.h
new file mode 100644
index 00000000..0345394a
--- /dev/null
+++ b/training/kbest_repository.h
@@ -0,0 +1,19 @@
+#ifndef _KBEST_REPOSITORY_H_
+#define _KBEST_REPOSITORY_H_
+
+#include <vector>
+#include "wordid.h"
+#include "ns.h"
+#include "sparse_vector.h"
+
+class KBestRepository {
+  struct HypInfo {
+    std::vector<WordID> words;
+    SparseVector<double> x;
+    SufficientStats score_stats;
+  };
+
+  std::vector<HypInfo> candidates;
+};
+
+#endif