pairwise ranking implemented

rank/xgboost_rank.h

@@ -94,20 +94,20 @@ public:
     inline void InitTrainer( void ) {
         base_gbm.InitTrainer();
         if( mparam.loss_type == PAIRWISE) {
-            evaluator_.AddEval( "pairwise" );
+            evaluator_.AddEval( "PAIR" );
         } else if( mparam.loss_type == MAP) {
             evaluator_.AddEval( "MAP" );
         } else {
             evaluator_.AddEval( "NDCG" );
         }
         evaluator_.Init();
+	sampler.AssignSampler(mparam.sampler_type);
     }
     /*!
     * \brief initialize the current data storage for model, if the model is used first time, call this function
     */
     inline void InitModel( void ) {
         base_gbm.InitModel();
-        mparam.AdjustBase();
     }
     /*!
     * \brief load model from stream
@@ -134,6 +134,7 @@ public:
     inline void DumpPath( FILE *fo, const RMatrix &data ) {
         base_gbm.DumpPath( fo, data.data );
     }
+    
     /*!
     * \brief save model to stream
     * \param fo output stream
@@ -142,6 +143,7 @@ public:
         base_gbm.SaveModel( fo );
         fo.Write( &mparam, sizeof(ModelParam) );
     }
+    
     /*!
      * \brief update the model for one iteration
      * \param iteration iteration number
@@ -177,7 +179,7 @@ public:
         const unsigned ndata = static_cast<unsigned>( data.Size() );
         #pragma omp parallel for schedule( static )
         for( unsigned j = 0; j < ndata; ++ j ) {
-            preds[j] = mparam.base_score + base_gbm.Predict( data.data, j, -1 );
+            preds[j] = base_gbm.Predict( data.data, j, -1 );
         }
     }
     
@@ -219,7 +221,7 @@ private:
         const unsigned ndata = static_cast<unsigned>( data.Size() );
         #pragma omp parallel for schedule( static )
         for( unsigned j = 0; j < ndata; ++ j ) {
-            preds[j] = mparam.base_score + base_gbm.InteractPredict( data.data, j, buffer_offset + j );
+            preds[j] = base_gbm.InteractPredict( data.data, j, buffer_offset + j );
         }
     }
     /*! \brief repredict trial */
@@ -238,7 +240,7 @@ private:
         const unsigned ndata = static_cast<unsigned>( data.Size() );
         #pragma omp parallel for schedule( static )
         for( unsigned j = 0; j < ndata; ++ j ) {
-            preds[j] = mparam.base_score + base_gbm.Predict( data.data, j, buffer_offset + j );
+            preds[j] = base_gbm.Predict( data.data, j, buffer_offset + j );
       
 	}
     }
@@ -254,13 +256,13 @@ private:
 	bool j_better;
 	float pred_diff,pred_diff_exp,first_order_gradient,second_order_gradient;
 	for(int i = 0; i < group_index.size() - 1; i++){
-	  xgboost::rank::sample::PairSamplerSet sampler;
+	  
-	  xgboost::rank::sample::Pairs pairs = sampler.GenPairs(preds,labels,group_index[i],group_index[i+1]);
+	  sample::Pairs pairs = sampler.GenPairs(preds,labels,group_index[i],group_index[i+1]);
-	  for(int j = group_index[i]; j < group_index[i+1]; j++){
+	  for(int j = group_index[i]; j < group_index[i + 1]; j++){
 	      std::vector<int> pair_instance = pairs.GetPairs(j);
+	      for(int k = 0; k < pair_instance.size(); k++){
 		 j_better =  labels[j] > labels[pair_instance[k]];
 	         if(j_better){
-	      for(int k = 0; k < pair_instance.size(); k++){
 	   	     pred_diff = preds[preds[j] - pair_instance[k]];
 		     pred_diff_exp =  j_better? expf(-pred_diff):expf(pred_diff);
                      first_order_gradient = mparam.FirstOrderGradient(pred_diff_exp);	    
@@ -285,17 +287,16 @@ private:
     
     /*! \brief training parameter for regression */
     struct ModelParam {
-        /* \brief global bias */
-        float base_score;
         /* \brief type of loss function */
         int loss_type;
         /* \brief number of features  */
         int num_feature;
         /*! \brief reserved field */
         int reserved[ 16 ];
+	/*! \brief sampler type */
+	int sampler_type;
         /*! \brief constructor */
         ModelParam( void ) {
-            base_score = 0.5f;
             loss_type  = 0;
             num_feature = 0;
             memset( reserved, 0, sizeof( reserved ) );
@@ -306,36 +307,11 @@ private:
         * \param val  value of the parameter
         */
         inline void SetParam( const char *name, const char *val ) {
-            if( !strcmp("base_score", name ) )  base_score = (float)atof( val );
             if( !strcmp("loss_type", name ) )   loss_type = atoi( val );
             if( !strcmp("bst:num_feature", name ) ) num_feature = atoi( val );
-        }
+	    if( !strcmp("rank:sampler",name)) sampler = atoi( val );
-        /*!
-        * \brief adjust base_score
-        */
-        inline void AdjustBase( void ) {
-            if( loss_type == 1 || loss_type == 2 ) {
-                utils::Assert( base_score > 0.0f && base_score < 1.0f, "sigmoid range constrain" );
-                base_score = - logf( 1.0f / base_score - 1.0f );
-            }
         }
 
-        /*!
-        * \brief transform the linear sum to prediction
-        * \param x linear sum of boosting ensemble
-        * \return transformed prediction
-        */
-        inline float PredTransform( float x ) {
-            switch( loss_type ) {
-            case PAIRWISE:
-            case MAP:
-            case NDCG:
-                return 1.0f/(1.0f + expf(-x));
-            default:
-                utils::Error("unknown loss_type");
-                return 0.0f;
-            }
-        }
 
         /*!
         * \brief calculate first order gradient of pairwise loss function(f(x) = ln(1+exp(-x)), 
@@ -358,57 +334,11 @@ private:
         inline float SecondOrderGradient( float pred_diff_exp ) const {
             return pred_diff_exp/pow(1 + pred_diff_exp,2);
         }
-
-        /*!
-         * \brief calculating the loss, given the predictions, labels and the loss type
-         * \param preds the given predictions
-         * \param labels the given labels
-         * \return the specified loss
-         */
-        inline float Loss(const std::vector<float> &preds, const std::vector<float> &labels) const {
-            switch( loss_type ) {
-            case kLinearSquare:
-                return SquareLoss(preds,labels);
-            case kLogisticNeglik:
-            case kLogisticClassify:
-                return NegLoglikelihoodLoss(preds,labels);
-            default:
-                utils::Error("unknown loss_type");
-                return 0.0f;
-            }
-        }
-
-        /*!
-         * \brief calculating the square loss, given the predictions and labels
-         * \param preds the given predictions
-         * \param labels the given labels
-         * \return the summation of square loss
-         */
-        inline float SquareLoss(const std::vector<float> &preds, const std::vector<float> &labels) const {
-            float ans = 0.0;
-            for(size_t i = 0; i < preds.size(); i++) {
-                float dif = preds[i] - labels[i];
-                ans += dif * dif;
-            }
-            return ans;
-        }
-
-        /*!
-         * \brief calculating the square loss, given the predictions and labels
-         * \param preds the given predictions
-         * \param labels the given labels
-         * \return the summation of square loss
-         */
-        inline float NegLoglikelihoodLoss(const std::vector<float> &preds, const std::vector<float> &labels) const {
-            float ans = 0.0;
-            for(size_t i = 0; i < preds.size(); i++)
-                ans -= labels[i] * logf(preds[i]) + ( 1 - labels[i] ) * logf(1 - preds[i]);
-            return ans;
-        }
     };
 private:
     int silent;
     RankEvalSet evaluator_;
+    sample::PairSamplerWrapper sampler;
     booster::GBMBase base_gbm;
     ModelParam   mparam;
     const RMatrix *train_;

rank/xgboost_rank_eval.h

@@ -46,6 +46,14 @@ bool PairValueComparer(const Pair &a, const Pair &b){
     return a.value_ < b.value_;
 }
 
+struct EvalPair : public IRankEvaluator{
+    virtual float Eval( const std::vector<float> &preds,
+                        const std::vector<float> &labels,
+                        const std::vector<int> &group_index  ) const {
+	return 0;
+    }  
+};
+
 /*! \brief Mean Average Precision */
 struct EvalMAP : public IRankEvaluator {
     virtual float Eval( const std::vector<float> &preds,
@@ -130,6 +138,7 @@ namespace rank {
 struct RankEvalSet {
 public:
     inline void AddEval( const char *name ) {
+        if( !strcmp( name, "PAIR" )) evals_.push_back( &pair_);
         if( !strcmp( name, "MAP") ) evals_.push_back( &map_ );
         if( !strcmp( name, "NDCG") ) evals_.push_back( &ndcg_ );
     }
@@ -144,12 +153,13 @@ public:
                       const std::vector<float> &labels,
                       const std::vector<int> &group_index ) const {
         for( size_t i = 0; i < evals_.size(); ++ i ) {
-            float res = evals_[i]->Eval( preds, labels );
+            float res = evals_[i]->Eval( preds, labels,group_index );
             fprintf( fo, "\t%s-%s:%f", evname, evals_[i]->Name(), res );
         }
     }
     
 private:
+    EvalPair pair_;
     EvalMAP map_;
     EvalNDCG ndcg_;
     std::vector<const IRankEvaluator*> evals_;

rank/xgboost_sample.h

@@ -1,21 +1,47 @@
 #ifndef _XGBOOST_SAMPLE_H_
 #define _XGBOOST_SAMPLE_H_
 
+#include<vector>
 #include"../utils/xgboost_utils.h"
 
 namespace xgboost {
   namespace rank {
     namespace sample {
 
+      /*
+       * \brief the data structure to maintain the sample pairs
+       */
       struct Pairs {
 
+      /*
+       * \brief constructor given the start and end offset of the sampling group
+       *        in overall instances
+       * \param start the begin index of the group
+       * \param end the end index of the group
+       */
+      Pairs(int start,int end):start_(start),end_(end_){
+	for(int i = start; i < end; i++){
+	  vector<int> v;
+	  pairs_.push_back(v);
+	}
+      }
       /*
        * \brief retrieve the related pair information of an data instances
        * \param index, the index of retrieved instance
        * \return the index of instances paired
        */
       std::vector<int> GetPairs(int index) {
-        utils::assert(index >= start_ && index < end_, "The query index out of sampling bound");
+        utils::assert(index >= start_ && index < end_,"The query index out of sampling bound");
+        return pairs_[index-start_];
+      }
+
+      /*
+       * \brief add in a sampled pair
+       * \param index the index of the instance to sample a friend
+       * \param paired_index the index of the instance sampled as a friend
+       */
+      void push(int index,int paired_index){
+	pairs_[index - start_].push_back(paired_index);
       }
       
       std::vector<std::vector<int>> pairs_;
@@ -23,6 +49,9 @@ namespace xgboost {
       int end_;
     };
 
+      /*
+       * \brief the interface of pair sampler
+       */
       struct IPairSampler {
 	  /*
 	   * \brief Generate sample pairs given the predcions, labels, the start and the end index 
@@ -36,29 +65,61 @@ namespace xgboost {
 	  virtual Pairs GenPairs(const std::vector<float> &preds,
 				 const std::vector<float> &labels,
 			         int start,int end) = 0;
+		
       };
       
-      /*! \brief a set of evaluators */
+      enum{
-        struct PairSamplerSet{
+	  BINARY_LINEAR_SAMPLER
-        public:
+      };
-            inline void AssignSampler( const char *name ){                
-                if( !strcmp( name, "rmse") ) evals_.push_back( &rmse_ );
-                if( !strcmp( name, "error") ) evals_.push_back( &error_ );
-                if( !strcmp( name, "logloss") ) evals_.push_back( &logloss_ );
-            }
       
+      /*! \brief A simple pair sampler when the rank relevence scale is binary
+       *         for each positive instance, we will pick a negative
+       *         instance and add in a pair. When using binary linear sampler, 
+       *         we should guarantee the labels are 0 or 1
+       */
+      struct BinaryLinearSampler:public IPairSampler{
+	virtual Pairs GenPairs(const std::vector<float> &preds,
+			       const std::vector<float> &labels,
+			       int start,int end) {
+  	    Pairs pairs(start,end);
+	    int pointer = 0, last_pointer = 0,index = start, interval = end - start;
+	    for(int i = start; i < end; i++){
+	      if(labels[i] == 1){
+		while(true){
+		  index = (++pointer) % interval + start;
+		  if(labels[index] == 0) break;
+		  if(pointer - last_pointer > interval) return pairs;
+		} 
+		pairs.push(i,index);
+		pairs.push(index,i);
+		last_pointer = pointer;
+	      }
+	    }
+	    return pairs; 
+	}	
+      };
+      
+      
+      /*! \brief Pair Sampler Wrapper*/
+        struct PairSamplerWrapper{
+        public:
+            inline void AssignSampler( int sampler_index ){                
+            
+	      switch(sampler_index){
+		case BINARY_LINEAR_SAMPLER:sampler_ = &binary_linear_sampler;break;
+	
+		default:utils::Error("Cannot find the specified sampler");
+	      }
+	    }
             
             Pairs GenPairs(const std::vector<float> &preds,
 			   const std::vector<float> &labels,
 			   int start,int end){
-			
+	      return sampler_.GenPairs(preds,labels,start,end);
-	      
 	    }
         private:
-            EvalRMSE  rmse_;
+	    BinaryLinearSampler binary_linear_sampler;
-            EvalError error_;
+	    IPairSampler *sampler_; 
-            EvalLogLoss logloss_;
-            std::vector<const IEvaluator*> evals_;  
         };
     }
   }