new feature generator is connected to gd.h - it uses new interactions…

… preprocessing and FTRL-like hash

vowpalwabbit/gd.h

@@ -10,6 +10,7 @@
 
 #include "parse_regressor.h"
 #include "constant.h"
+#include "interactions.h"
 
 namespace GD{
   LEARNER::base_learner* setup(vw& all);
@@ -69,34 +70,7 @@ namespace GD{
     for (unsigned char* i = ec.indices.begin; i != ec.indices.end; i++)
       foreach_feature<R,T>(all.reg.weight_vector, all.reg.weight_mask, ec.atomics[*i].begin, ec.atomics[*i].end, dat, offset);
 
-    for (vector<string>::iterator i = all.pairs.begin(); i != all.pairs.end();i++) {
-      if (ec.atomics[(unsigned char)(*i)[0]].size() > 0) {
-        v_array<feature> temp = ec.atomics[(unsigned char)(*i)[0]];
-        for (; temp.begin != temp.end; temp.begin++)
-        {
-          uint32_t halfhash = quadratic_constant * (temp.begin->weight_index) + offset;
-
-          foreach_feature<R,T>(all.reg.weight_vector, all.reg.weight_mask, ec.atomics[(unsigned char)(*i)[1]].begin, ec.atomics[(unsigned char)(*i)[1]].end, dat, 
-                               halfhash, temp.begin->x);
-        }
-      }
-    }
-
-    for (vector<string>::iterator i = all.triples.begin(); i != all.triples.end();i++) {
-      if ((ec.atomics[(unsigned char)(*i)[0]].size() == 0) || (ec.atomics[(unsigned char)(*i)[1]].size() == 0) || (ec.atomics[(unsigned char)(*i)[2]].size() == 0)) { continue; }
-      v_array<feature> temp1 = ec.atomics[(unsigned char)(*i)[0]];
-      for (; temp1.begin != temp1.end; temp1.begin++) {
-        v_array<feature> temp2 = ec.atomics[(unsigned char)(*i)[1]];
-        for (; temp2.begin != temp2.end; temp2.begin++) {
-
-          uint32_t a = temp1.begin->weight_index;
-          uint32_t b = temp2.begin->weight_index;
-          uint32_t halfhash = cubic_constant2 * (cubic_constant * a + b) + offset;
-          float mult = temp1.begin->x * temp2.begin->x;
-          foreach_feature<R,T>(all.reg.weight_vector, all.reg.weight_mask, ec.atomics[(unsigned char)(*i)[2]].begin, ec.atomics[(unsigned char)(*i)[2]].end, dat, halfhash, mult);
-        }
-      }
-    }
+    INTERACTIONS::generate_interactions<R,S,T>(all, ec, dat);
   }
 
   // iterate through all namespaces and quadratic&cubic features, callback function T(some_data_R, feature_value_x, feature_weight)

vowpalwabbit/parser.cc

@@ -50,6 +50,7 @@ namespace po = boost::program_options;
 #include "unique_sort.h"
 #include "constant.h"
 #include "vw.h"
+#include "interactions.h"
 
 using namespace std;
 
@@ -841,22 +842,13 @@ void setup_example(vw& all, example* ae)
       ae->total_sum_feat_sq += ae->sum_feat_sq[*i];
     }
 
-  for (vector<string>::iterator i = all.pairs.begin(); i != all.pairs.end();i++)
-    {
-      ae->num_features 
-	+= ae->atomics[(int)(*i)[0]].size()
-	*ae->atomics[(int)(*i)[1]].size();
-      ae->total_sum_feat_sq += ae->sum_feat_sq[(int)(*i)[0]]*ae->sum_feat_sq[(int)(*i)[1]];
-    }
-
-  for (vector<string>::iterator i = all.triples.begin(); i != all.triples.end();i++)
-    {
-      ae->num_features 
-	+= ae->atomics[(int)(*i)[0]].size()
-	*ae->atomics[(int)(*i)[1]].size()
-	*ae->atomics[(int)(*i)[2]].size();
-      ae->total_sum_feat_sq += ae->sum_feat_sq[(int)(*i)[0]] * ae->sum_feat_sq[(int)(*i)[1]] * ae->sum_feat_sq[(int)(*i)[2]];
-    }
+  // generate atomic features for all interactions
+  size_t new_features_cnt;
+  float new_features_sum_feat_sq;
+  INTERACTIONS::eval_count_of_generated_ft(all, *ae, new_features_cnt, new_features_sum_feat_sq);
+  ae->num_features += new_features_cnt;
+  ae->total_sum_feat_sq += new_features_sum_feat_sq;
+
 }
 }