view release on metacpan or  search on metacpan

xgboost/include/xgboost/data.h  view on Meta::CPAN

   */
  inline bool Load(dmlc::Stream* fi);
  /*! \brief constructor */
  RowSet() : size_(0) {}

 private:
  /*! \brief The internal data structure of size */
  uint64_t size_;
  /*! \brief The internal data structure of row set if not all*/
  std::vector<bst_uint> rows_;
};

/*!
 * \brief Internal data structured used by XGBoost during training.
 *  There are two ways to create a customized DMatrix that reads in user defined-format.
 *
 *  - Provide a dmlc::Parser and pass into the DMatrix::Create
 *  - Alternatively, if data can be represented by an URL, define a new dmlc::Parser and register by DMLC_REGISTER_DATA_PARSER;
 *      - This works best for user defined data input source, such as data-base, filesystem.
 *  - Provide a DataSource, that can be passed to DMatrix::Create
 *      This can be used to re-use inmemory data structure into DMatrix.
 */
class DMatrix {
 public:
  /*! \brief default constructor */
  DMatrix() : cache_learner_ptr_(nullptr) {}
  /*! \brief meta information of the dataset */
  virtual MetaInfo& info() = 0;
  /*! \brief meta information of the dataset */
  virtual const MetaInfo& info() const = 0;
  /*!
   * \brief get the row iterator, reset to beginning position
   * \note Only either RowIterator or  column Iterator can be active.
   */
  virtual dmlc::DataIter<RowBatch>* RowIterator() = 0;
  /*!\brief get column iterator, reset to the beginning position */
  virtual dmlc::DataIter<ColBatch>* ColIterator() = 0;
  /*!
   * \brief get the column iterator associated with subset of column features.
   * \param fset is the list of column index set that must be contained in the returning Column iterator
   * \return the column iterator, initialized so that it reads the elements in fset
   */
  virtual dmlc::DataIter<ColBatch>* ColIterator(const std::vector<bst_uint>& fset) = 0;
  /*!
   * \brief check if column access is supported, if not, initialize column access.
   * \param enabled whether certain feature should be included in column access.
   * \param subsample subsample ratio when generating column access.
   * \param max_row_perbatch auxiliary information, maximum row used in each column batch.
   *         this is a hint information that can be ignored by the implementation.
   * \return Number of column blocks in the column access.
   */
  virtual void InitColAccess(const std::vector<bool>& enabled,
                             float subsample,
                             size_t max_row_perbatch) = 0;
  // the following are column meta data, should be able to answer them fast.
  /*! \return whether column access is enabled */
  virtual bool HaveColAccess() const = 0;
  /*! \return Whether the data columns single column block. */
  virtual bool SingleColBlock() const = 0;
  /*! \brief get number of non-missing entries in column */
  virtual size_t GetColSize(size_t cidx) const = 0;
  /*! \brief get column density */
  virtual float GetColDensity(size_t cidx) const = 0;
  /*! \return reference of buffered rowset, in column access */
  virtual const RowSet& buffered_rowset() const = 0;
  /*! \brief virtual destructor */
  virtual ~DMatrix() {}
  /*!
   * \brief Save DMatrix to local file.
   *  The saved file only works for non-sharded dataset(single machine training).
   *  This API is deprecated and dis-encouraged to use.
   * \param fname The file name to be saved.
   * \return The created DMatrix.
   */
  virtual void SaveToLocalFile(const std::string& fname);
  /*!
   * \brief Load DMatrix from URI.
   * \param uri The URI of input.
   * \param silent Whether print information during loading.
   * \param load_row_split Flag to read in part of rows, divided among the workers in distributed mode.
   * \param file_format The format type of the file, used for dmlc::Parser::Create.
   *   By default "auto" will be able to load in both local binary file.
   * \return The created DMatrix.
   */
  static DMatrix* Load(const std::string& uri,
                       bool silent,
                       bool load_row_split,
                       const std::string& file_format = "auto");
  /*!
   * \brief create a new DMatrix, by wrapping a row_iterator, and meta info.
   * \param source The source iterator of the data, the create function takes ownership of the source.
   * \param cache_prefix The path to prefix of temporary cache file of the DMatrix when used in external memory mode.
   *     This can be nullptr for common cases, and in-memory mode will be used.
   * \return a Created DMatrix.
   */
  static DMatrix* Create(std::unique_ptr<DataSource>&& source,
                         const std::string& cache_prefix = "");
  /*!
   * \brief Create a DMatrix by loading data from parser.
   *  Parser can later be deleted after the DMatrix i created.
   * \param parser The input data parser
   * \param cache_prefix The path to prefix of temporary cache file of the DMatrix when used in external memory mode.
   *     This can be nullptr for common cases, and in-memory mode will be used.
   * \sa dmlc::Parser
   * \note dmlc-core provides efficient distributed data parser for libsvm format.
   *  User can create and register customized parser to load their own format using DMLC_REGISTER_DATA_PARSER.
   *  See "dmlc-core/include/dmlc/data.h" for detail.
   * \return A created DMatrix.
   */
  static DMatrix* Create(dmlc::Parser<uint32_t>* parser,
                         const std::string& cache_prefix = "");

 private:
  // allow learner class to access this field.
  friend class LearnerImpl;
  /*! \brief public field to back ref cached matrix. */
  LearnerImpl* cache_learner_ptr_;
};

// implementation of inline functions
inline bst_uint RowSet::operator[](size_t i) const {
  return rows_.size() == 0 ? i : rows_[i];
}