c_api.h

Go to the documentation of this file.

#ifndef XGBOOST_C_API_H_
#define XGBOOST_C_API_H_

#ifdef __cplusplus
#define XGB_EXTERN_C extern "C"
#include <cstdio>
#include <cstdint>
#else
#define XGB_EXTERN_C
#include <stdio.h>
#include <stdint.h>
#endif  // __cplusplus

#if defined(_MSC_VER) || defined(_WIN32)
#define XGB_DLL XGB_EXTERN_C __declspec(dllexport)
#else
#define XGB_DLL XGB_EXTERN_C __attribute__ ((visibility ("default")))
#endif  // defined(_MSC_VER) || defined(_WIN32)

// manually define unsigned long
typedef uint64_t bst_ulong;  // NOLINT(*)

typedef void *DMatrixHandle;  // NOLINT(*)
typedef void *BoosterHandle;  // NOLINT(*)

XGB_DLL void XGBoostVersion(int* major, int* minor, int* patch);

XGB_DLL const char *XGBGetLastError(void);

XGB_DLL int XGBRegisterLogCallback(void (*callback)(const char*));

XGB_DLL int XGDMatrixCreateFromFile(const char *fname,
                                    int silent,
                                    DMatrixHandle *out);

XGB_DLL int XGDMatrixCreateFromCSREx(const size_t* indptr,
                                     const unsigned* indices,
                                     const float* data,
                                     size_t nindptr,
                                     size_t nelem,
                                     size_t num_col,
                                     DMatrixHandle* out);
XGB_DLL int XGDMatrixCreateFromCSCEx(const size_t* col_ptr,
                                     const unsigned* indices,
                                     const float* data,
                                     size_t nindptr,
                                     size_t nelem,
                                     size_t num_row,
                                     DMatrixHandle* out);

XGB_DLL int XGDMatrixCreateFromMat(const float *data,
                                   bst_ulong nrow,
                                   bst_ulong ncol,
                                   float missing,
                                   DMatrixHandle *out);
XGB_DLL int XGDMatrixCreateFromMat_omp(const float *data,  // NOLINT
                                       bst_ulong nrow, bst_ulong ncol,
                                       float missing, DMatrixHandle *out,
                                       int nthread);
XGB_DLL int XGDMatrixCreateFromDT(void** data,
                                  const char ** feature_stypes,
                                  bst_ulong nrow,
                                  bst_ulong ncol,
                                  DMatrixHandle* out,
                                  int nthread);

/*
 * ========================== Begin data callback APIs =========================
 *
 * Short notes for data callback
 *
 * There are 2 sets of data callbacks for DMatrix.  The first one is currently exclusively
 * used by JVM packages.  It uses `XGBoostBatchCSR` to accept batches for CSR formated
 * input, and concatenate them into 1 final big CSR.  The related functions are:
 *
 * - XGBCallbackSetData
 * - XGBCallbackDataIterNext
 * - XGDMatrixCreateFromDataIter
 *
 * Another set is used by Quantile based DMatrix (used by hist algorithm) for reducing
 * memory usage.  Currently only GPU implementation is available.  It accept foreign data
 * iterators as callbacks and works similar to external memory.  For GPU Hist, the data is
 * first compressed by quantile sketching then merged.  This is particular useful for
 * distributed setting as it eliminates 2 copies of data.  1 by a `concat` from external
 * library to make the data into a blob for normal DMatrix initialization, another by the
 * internal CSR copy of DMatrix.  Related functions are:
 *
 * - XGProxyDMatrixCreate
 * - XGDMatrixCallbackNext
 * - DataIterResetCallback
 * - XGDeviceQuantileDMatrixSetDataCudaArrayInterface
 * - XGDeviceQuantileDMatrixSetDataCudaColumnar
 * - ... (data setters)
 */

/*  ==== First set of callback functions, used exclusively by JVM packages. ==== */

typedef void *DataIterHandle;  // NOLINT(*)
typedef void *DataHolderHandle;  // NOLINT(*)


typedef struct {  // NOLINT(*)
  size_t size;
  /* \brief number of columns in the minibatch. */
  size_t columns;
#ifdef __APPLE__
  /* Necessary as Java on MacOS defines jlong as long int
   * and gcc defines int64_t as long long int. */
  long* offset; // NOLINT(*)
#else
  int64_t* offset;  // NOLINT(*)
#endif  // __APPLE__

  float* label;
  float* weight;
  int* index;
  float* value;
} XGBoostBatchCSR;

XGB_EXTERN_C typedef int XGBCallbackSetData(  // NOLINT(*)
    DataHolderHandle handle, XGBoostBatchCSR batch);

XGB_EXTERN_C typedef int XGBCallbackDataIterNext(  // NOLINT(*)
    DataIterHandle data_handle, XGBCallbackSetData *set_function,
    DataHolderHandle set_function_handle);

XGB_DLL int XGDMatrixCreateFromDataIter(
    DataIterHandle data_handle,
    XGBCallbackDataIterNext* callback,
    const char* cache_info,
    DMatrixHandle *out);

/*  == Second set of callback functions, used by constructing Quantile based DMatrix. ===
 *
 * Short note for how to use the second set of callback for GPU Hist tree method.
 *
 * Step 0: Define a data iterator with 2 methods `reset`, and `next`.
 * Step 1: Create a DMatrix proxy by `XGProxyDMatrixCreate` and hold the handle.
 * Step 2: Pass the iterator handle, proxy handle and 2 methods into
 *         `XGDeviceQuantileDMatrixCreateFromCallback`.
 * Step 3: Call appropriate data setters in `next` functions.
 *
 * See test_iterative_device_dmatrix.cu or Python interface for examples.
 */

XGB_DLL int XGProxyDMatrixCreate(DMatrixHandle* out);

XGB_EXTERN_C typedef int XGDMatrixCallbackNext(DataIterHandle iter);  // NOLINT(*)

XGB_EXTERN_C typedef void DataIterResetCallback(DataIterHandle handle); // NOLINT(*)

XGB_DLL int XGDeviceQuantileDMatrixCreateFromCallback(
    DataIterHandle iter, DMatrixHandle proxy, DataIterResetCallback *reset,
    XGDMatrixCallbackNext *next, float missing, int nthread, int max_bin,
    DMatrixHandle *out);
XGB_DLL int XGDeviceQuantileDMatrixSetDataCudaArrayInterface(
    DMatrixHandle handle,
    const char* c_interface_str);
XGB_DLL int XGDeviceQuantileDMatrixSetDataCudaColumnar(
    DMatrixHandle handle,
    const char* c_interface_str);
/*
 * ==========================- End data callback APIs ==========================
 */



XGB_DLL int XGDMatrixSliceDMatrix(DMatrixHandle handle,
                                  const int *idxset,
                                  bst_ulong len,
                                  DMatrixHandle *out);
XGB_DLL int XGDMatrixSliceDMatrixEx(DMatrixHandle handle,
                                    const int *idxset,
                                    bst_ulong len,
                                    DMatrixHandle *out,
                                    int allow_groups);
XGB_DLL int XGDMatrixFree(DMatrixHandle handle);
XGB_DLL int XGDMatrixSaveBinary(DMatrixHandle handle,
                                const char *fname, int silent);

XGB_DLL int XGDMatrixSetInfoFromInterface(DMatrixHandle handle,
                                          char const* field,
                                          char const* c_interface_str);

XGB_DLL int XGDMatrixSetFloatInfo(DMatrixHandle handle,
                                  const char *field,
                                  const float *array,
                                  bst_ulong len);
XGB_DLL int XGDMatrixSetUIntInfo(DMatrixHandle handle,
                                 const char *field,
                                 const unsigned *array,
                                 bst_ulong len);

XGB_DLL int XGDMatrixSetStrFeatureInfo(DMatrixHandle handle, const char *field,
                                       const char **features,
                                       const bst_ulong size);

XGB_DLL int XGDMatrixGetStrFeatureInfo(DMatrixHandle handle, const char *field,
                                       bst_ulong *size,
                                       const char ***out_features);

XGB_DLL int XGDMatrixSetGroup(DMatrixHandle handle,
                              const unsigned *group,
                              bst_ulong len);

XGB_DLL int XGDMatrixGetFloatInfo(const DMatrixHandle handle,
                                  const char *field,
                                  bst_ulong* out_len,
                                  const float **out_dptr);
XGB_DLL int XGDMatrixGetUIntInfo(const DMatrixHandle handle,
                                 const char *field,
                                 bst_ulong* out_len,
                                 const unsigned **out_dptr);
XGB_DLL int XGDMatrixNumRow(DMatrixHandle handle,
                            bst_ulong *out);
XGB_DLL int XGDMatrixNumCol(DMatrixHandle handle,
                            bst_ulong *out);
// --- start XGBoost class
XGB_DLL int XGBoosterCreate(const DMatrixHandle dmats[],
                            bst_ulong len,
                            BoosterHandle *out);
XGB_DLL int XGBoosterFree(BoosterHandle handle);

XGB_DLL int XGBoosterSetParam(BoosterHandle handle,
                              const char *name,
                              const char *value);

XGB_DLL int XGBoosterGetNumFeature(BoosterHandle handle,
                                   bst_ulong *out);

XGB_DLL int XGBoosterUpdateOneIter(BoosterHandle handle,
                                   int iter,
                                   DMatrixHandle dtrain);
XGB_DLL int XGBoosterBoostOneIter(BoosterHandle handle,
                                  DMatrixHandle dtrain,
                                  float *grad,
                                  float *hess,
                                  bst_ulong len);
XGB_DLL int XGBoosterEvalOneIter(BoosterHandle handle,
                                 int iter,
                                 DMatrixHandle dmats[],
                                 const char *evnames[],
                                 bst_ulong len,
                                 const char **out_result);
XGB_DLL int XGBoosterPredict(BoosterHandle handle,
                             DMatrixHandle dmat,
                             int option_mask,
                             unsigned ntree_limit,
                             int training,
                             bst_ulong *out_len,
                             const float **out_result);

/*
 * ========================== Begin Serialization APIs =========================
 */
/*
 * Short note for serialization APIs.  There are 3 different sets of serialization API.
 *
 * - Functions with the term "Model" handles saving/loading XGBoost model like trees or
 *   linear weights.  Striping out parameters configuration like training algorithms or
 *   CUDA device ID.  These functions are designed to let users reuse the trained model
 *   for different tasks, examples are prediction, training continuation or model
 *   interpretation.
 *
 * - Functions with the term "Config" handles save/loading configuration.  It helps user
 *   to study the internal of XGBoost.  Also user can use the load method for specifying
 *   paramters in a structured way.  These functions are introduced in 1.0.0, and are not
 *   yet stable.
 *
 * - Functions with the term "Serialization" are combined of above two.  They are used in
 *   situations like check-pointing, or continuing training task in distributed
 *   environment.  In these cases the task must be carried out without any user
 *   intervention.
 */

XGB_DLL int XGBoosterLoadModel(BoosterHandle handle,
                               const char *fname);
XGB_DLL int XGBoosterSaveModel(BoosterHandle handle,
                               const char *fname);
XGB_DLL int XGBoosterLoadModelFromBuffer(BoosterHandle handle,
                                         const void *buf,
                                         bst_ulong len);
XGB_DLL int XGBoosterGetModelRaw(BoosterHandle handle, bst_ulong *out_len,
                                 const char **out_dptr);

XGB_DLL int XGBoosterSerializeToBuffer(BoosterHandle handle, bst_ulong *out_len,
                                       const char **out_dptr);
XGB_DLL int XGBoosterUnserializeFromBuffer(BoosterHandle handle,
                                           const void *buf, bst_ulong len);

XGB_DLL int XGBoosterLoadRabitCheckpoint(BoosterHandle handle,
                                         int* version);

XGB_DLL int XGBoosterSaveRabitCheckpoint(BoosterHandle handle);


XGB_DLL int XGBoosterSaveJsonConfig(BoosterHandle handle, bst_ulong *out_len,
                                    char const **out_str);
XGB_DLL int XGBoosterLoadJsonConfig(BoosterHandle handle,
                                    char const *json_parameters);
/*
 * =========================== End Serialization APIs ==========================
 */


XGB_DLL int XGBoosterDumpModel(BoosterHandle handle,
                               const char *fmap,
                               int with_stats,
                               bst_ulong *out_len,
                               const char ***out_dump_array);

XGB_DLL int XGBoosterDumpModelEx(BoosterHandle handle,
                                 const char *fmap,
                                 int with_stats,
                                 const char *format,
                                 bst_ulong *out_len,
                                 const char ***out_dump_array);

XGB_DLL int XGBoosterDumpModelWithFeatures(BoosterHandle handle,
                                           int fnum,
                                           const char **fname,
                                           const char **ftype,
                                           int with_stats,
                                           bst_ulong *out_len,
                                           const char ***out_models);

XGB_DLL int XGBoosterDumpModelExWithFeatures(BoosterHandle handle,
                                             int fnum,
                                             const char **fname,
                                             const char **ftype,
                                             int with_stats,
                                             const char *format,
                                             bst_ulong *out_len,
                                             const char ***out_models);

XGB_DLL int XGBoosterGetAttr(BoosterHandle handle,
                             const char* key,
                             const char** out,
                             int *success);
XGB_DLL int XGBoosterSetAttr(BoosterHandle handle,
                             const char* key,
                             const char* value);
XGB_DLL int XGBoosterGetAttrNames(BoosterHandle handle,
                                  bst_ulong* out_len,
                                  const char*** out);
#endif  // XGBOOST_C_API_H_