From 83eb31deb8a2056c098715c8cb29f2498fc213c3 Mon Sep 17 00:00:00 2001
From: Patrick Simianer <p@simianer.de>
Date: Thu, 8 Sep 2011 00:06:52 +0200
Subject: a lot of stuff, fast_sparse_vector, perceptron, removed sofia, sample
 [...]

---
 dtrain/sample.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)
 create mode 100644 dtrain/sample.h

(limited to 'dtrain/sample.h')

diff --git a/dtrain/sample.h b/dtrain/sample.h
new file mode 100644
index 00000000..b9bc4461
--- /dev/null
+++ b/dtrain/sample.h
@@ -0,0 +1,52 @@
+#include "kbestget.h"
+
+
+namespace dtrain
+{
+
+
+struct TPair
+{
+  double type;
+  SparseVector<double> first;
+  SparseVector<double> second;
+};
+
+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)
+{
+
+}
+
+void
+sample_random_pos()
+{
+  if ( rand() % 2 ) { // sample it?
+}*/
+
+
+} // namespace
+
-- 
cgit v1.2.3