Class Bin

include/LightGBM/bin.h:291–460

! * \brief Interface for bin data. This class will store bin data for one feature. * unlike OrderedBin, this class will store data by original order. * Note that it may cause cache misses when construct histogram, * but it doesn't need to re-order operation, So it will be faster than OrderedBin for dense feature */

*        but it doesn't need to re-order operation, So it will be faster than OrderedBin for dense feature
*/
class Bin {
 public:
  /*! \brief virtual destructor */
  virtual ~Bin() {}
  /*!
  * \brief Push one record
  * \pram tid Thread id
  * \param idx Index of record
  * \param value bin value of record
  */
  virtual void Push(int tid, data_size_t idx, uint32_t value) = 0;


  virtual void CopySubset(const Bin* full_bin, const data_size_t* used_indices, data_size_t num_used_indices) = 0;
  /*!
  * \brief Get bin iterator of this bin for specific feature
  * \param min_bin min_bin of current used feature
  * \param max_bin max_bin of current used feature
  * \param default_bin default bin if bin not in [min_bin, max_bin]
  * \return Iterator of this bin
  */
  virtual BinIterator* GetIterator(uint32_t min_bin, uint32_t max_bin, uint32_t default_bin) const = 0;

  /*!
  * \brief Save binary data to file
  * \param file File want to write
  */
  virtual void SaveBinaryToFile(const VirtualFileWriter* writer) const = 0;

  /*!
  * \brief Load from memory
  * \param memory
  * \param local_used_indices
  */
  virtual void LoadFromMemory(const void* memory,
    const std::vector<data_size_t>& local_used_indices) = 0;

  /*!
  * \brief Get sizes in byte of this object
  */
  virtual size_t SizesInByte() const = 0;

  /*! \brief Number of all data */
  virtual data_size_t num_data() const = 0;

  virtual void ReSize(data_size_t num_data) = 0;

  /*!
  * \brief Construct histogram of this feature,
  *        Note: We use ordered_gradients and ordered_hessians to improve cache hit chance
  *        The naive solution is using gradients[data_indices[i]] for data_indices[i] to get gradients,
           which is not cache friendly, since the access of memory is not continuous.
  *        ordered_gradients and ordered_hessians are preprocessed, and they are re-ordered by data_indices.
  *        Ordered_gradients[i] is aligned with data_indices[i]'s gradients (same for ordered_hessians).
  * \param data_indices Used data indices in current leaf
  * \param num_data Number of used data
  * \param ordered_gradients Pointer to gradients, the data_indices[i]-th data's gradient is ordered_gradients[i]
  * \param ordered_hessians Pointer to hessians, the data_indices[i]-th data's hessian is ordered_hessians[i]