Add check to prevent out of index lookup in the position discount tab…

…le. Add debug logging to report number of queries found in the data.

include/LightGBM/metric.h

@@ -103,6 +103,14 @@ class DCGCalculator {
   static double CalMaxDCGAtK(data_size_t k,
     const label_t* label, data_size_t num_data);
 
+
+  /*!
+  * \brief Check the metadata for NDCG and lambdarank
+  * \param metadata Metadata
+  * \param num_queries Number of queries
+  */
+  static void CheckMetadata(const Metadata& metadata, data_size_t num_queries);
+
   /*!
   * \brief Check the label range for NDCG and lambdarank
   * \param label Pointer of label

src/io/metadata.cpp

@@ -162,6 +162,8 @@ void Metadata::CheckOrPartition(data_size_t num_all_data, const std::vector<data
       for (size_t i = 0; i < tmp_buffer.size(); ++i) {
         query_boundaries_[i + 1] = query_boundaries_[i] + tmp_buffer[i];
       }
+      Log::Info("Number of queries: %i. Average number of rows per query: %f.",
+        static_cast<int>(num_queries_), static_cast<double>(num_data_) / num_queries_);
       LoadQueryWeights();
       queries_.clear();
     }

src/metric/dcg_calculator.cpp

@@ -152,6 +152,19 @@ void DCGCalculator::CalDCG(const std::vector<data_size_t>& ks, const label_t* la
   }
 }
 
+void DCGCalculator::CheckMetadata(const Metadata& metadata, data_size_t num_queries) {
+  const data_size_t* query_boundaries = metadata.query_boundaries();
+  if (num_queries > 0 && query_boundaries != nullptr) {
+    for (data_size_t i = 0; i < num_queries; i++) {
+      data_size_t num_rows = query_boundaries[i + 1] - query_boundaries[i];
+      if (num_rows > kMaxPosition) {
+        Log::Fatal("Number of rows %i exceeds upper limit of %i for a query", static_cast<int>(num_rows), static_cast<int>(kMaxPosition));
+      }
+    }
+  }
+}
+
+
 void DCGCalculator::CheckLabel(const label_t* label, data_size_t num_data) {
   for (data_size_t i = 0; i < num_data; ++i) {
     label_t delta = std::fabs(label[i] - static_cast<int>(label[i]));

src/objective/rank_objective.hpp

@@ -120,6 +120,7 @@ class LambdarankNDCG : public RankingObjective {
 
   void Init(const Metadata& metadata, data_size_t num_data) override {
     RankingObjective::Init(metadata, num_data);
+    DCGCalculator::CheckMetadata(metadata, num_queries_);
     DCGCalculator::CheckLabel(label_, num_data_);
     inverse_max_dcgs_.resize(num_queries_);
 #pragma omp parallel for schedule(static)