355 lines
13 KiB
C
355 lines
13 KiB
C
/*!
|
|
* Copyright (c) 2014 by Contributors
|
|
* \file xgboost_wrapper.h
|
|
* \author Tianqi Chen
|
|
* \brief a C style wrapper of xgboost
|
|
* can be used to create wrapper of other languages
|
|
*/
|
|
#ifndef XGBOOST_WRAPPER_H_
|
|
#define XGBOOST_WRAPPER_H_
|
|
|
|
#ifdef __cplusplus
|
|
#define XGB_EXTERN_C extern "C"
|
|
#endif
|
|
|
|
#if defined(_MSC_VER) || defined(_WIN32)
|
|
#define XGB_DLL XGB_EXTERN_C __declspec(dllexport)
|
|
#else
|
|
#define XGB_DLL XGB_EXTERN_C
|
|
#endif
|
|
// manually define unsign long
|
|
typedef unsigned long bst_ulong; // NOLINT(*)
|
|
|
|
/*! \brief handle to DMatrix */
|
|
typedef void *DMatrixHandle;
|
|
/*! \brief handle to Booster */
|
|
typedef void *BoosterHandle;
|
|
|
|
/*!
|
|
* \brief get string message of the last error
|
|
*
|
|
* all function in this file will return 0 when success
|
|
* and -1 when an error occured,
|
|
* XGBGetLastError can be called to retrieve the error
|
|
*
|
|
* this function is threadsafe and can be called by different thread
|
|
* \return const char* error inforomation
|
|
*/
|
|
XGB_DLL const char *XGBGetLastError();
|
|
|
|
/*!
|
|
* \brief load a data matrix
|
|
* \param fname the name of the file
|
|
* \param silent whether print messages during loading
|
|
* \param out a loaded data matrix
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixCreateFromFile(const char *fname,
|
|
int silent,
|
|
DMatrixHandle *out);
|
|
|
|
/*!
|
|
* \brief create a matrix content from csr format
|
|
* \param indptr pointer to row headers
|
|
* \param indices findex
|
|
* \param data fvalue
|
|
* \param nindptr number of rows in the matix + 1
|
|
* \param nelem number of nonzero elements in the matrix
|
|
* \param out created dmatrix
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixCreateFromCSR(const bst_ulong *indptr,
|
|
const unsigned *indices,
|
|
const float *data,
|
|
bst_ulong nindptr,
|
|
bst_ulong nelem,
|
|
DMatrixHandle *out);
|
|
/*!
|
|
* \brief create a matrix content from CSC format
|
|
* \param col_ptr pointer to col headers
|
|
* \param indices findex
|
|
* \param data fvalue
|
|
* \param nindptr number of rows in the matix + 1
|
|
* \param nelem number of nonzero elements in the matrix
|
|
* \param out created dmatrix
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixCreateFromCSC(const bst_ulong *col_ptr,
|
|
const unsigned *indices,
|
|
const float *data,
|
|
bst_ulong nindptr,
|
|
bst_ulong nelem,
|
|
DMatrixHandle *out);
|
|
/*!
|
|
* \brief create matrix content from dense matrix
|
|
* \param data pointer to the data space
|
|
* \param nrow number of rows
|
|
* \param ncol number columns
|
|
* \param missing which value to represent missing value
|
|
* \param out created dmatrix
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixCreateFromMat(const float *data,
|
|
bst_ulong nrow,
|
|
bst_ulong ncol,
|
|
float missing,
|
|
DMatrixHandle *out);
|
|
/*!
|
|
* \brief create a new dmatrix from sliced content of existing matrix
|
|
* \param handle instance of data matrix to be sliced
|
|
* \param idxset index set
|
|
* \param len length of index set
|
|
* \param out a sliced new matrix
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixSliceDMatrix(DMatrixHandle handle,
|
|
const int *idxset,
|
|
bst_ulong len,
|
|
DMatrixHandle *out);
|
|
/*!
|
|
* \brief free space in data matrix
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixFree(void *handle);
|
|
/*!
|
|
* \brief load a data matrix into binary file
|
|
* \param handle a instance of data matrix
|
|
* \param fname file name
|
|
* \param silent print statistics when saving
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixSaveBinary(DMatrixHandle handle,
|
|
const char *fname, int silent);
|
|
/*!
|
|
* \brief set float vector to a content in info
|
|
* \param handle a instance of data matrix
|
|
* \param field field name, can be label, weight
|
|
* \param array pointer to float vector
|
|
* \param len length of array
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixSetFloatInfo(DMatrixHandle handle,
|
|
const char *field,
|
|
const float *array,
|
|
bst_ulong len);
|
|
/*!
|
|
* \brief set uint32 vector to a content in info
|
|
* \param handle a instance of data matrix
|
|
* \param field field name
|
|
* \param array pointer to float vector
|
|
* \param len length of array
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixSetUIntInfo(DMatrixHandle handle,
|
|
const char *field,
|
|
const unsigned *array,
|
|
bst_ulong len);
|
|
/*!
|
|
* \brief set label of the training matrix
|
|
* \param handle a instance of data matrix
|
|
* \param group pointer to group size
|
|
* \param len length of array
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixSetGroup(DMatrixHandle handle,
|
|
const unsigned *group,
|
|
bst_ulong len);
|
|
/*!
|
|
* \brief get float info vector from matrix
|
|
* \param handle a instance of data matrix
|
|
* \param field field name
|
|
* \param out_len used to set result length
|
|
* \param out_dptr pointer to the result
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixGetFloatInfo(const DMatrixHandle handle,
|
|
const char *field,
|
|
bst_ulong* out_len,
|
|
const float **out_dptr);
|
|
/*!
|
|
* \brief get uint32 info vector from matrix
|
|
* \param handle a instance of data matrix
|
|
* \param field field name
|
|
* \param out_ptr pointer to the result
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixGetUIntInfo(const DMatrixHandle handle,
|
|
const char *field,
|
|
bst_ulong* out_len,
|
|
const unsigned **out_dptr);
|
|
/*!
|
|
* \brief get number of rows
|
|
* \param handle the handle to the DMatrix
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixNumRow(DMatrixHandle handle,
|
|
bst_ulong *out);
|
|
/*!
|
|
* \brief get number of columns
|
|
* \param handle the handle to the DMatrix
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGDMatrixNumCol(DMatrixHandle handle,
|
|
bst_ulong *out);
|
|
// --- start XGBoost class
|
|
/*!
|
|
* \brief create xgboost learner
|
|
* \param dmats matrices that are set to be cached
|
|
* \param len length of dmats
|
|
* \param out handle to the result booster
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterCreate(void* dmats[],
|
|
bst_ulong len,
|
|
BoosterHandle *out);
|
|
/*!
|
|
* \brief free obj in handle
|
|
* \param handle handle to be freed
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterFree(BoosterHandle handle);
|
|
|
|
/*!
|
|
* \brief set parameters
|
|
* \param handle handle
|
|
* \param name parameter name
|
|
* \param val value of parameter
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterSetParam(BoosterHandle handle,
|
|
const char *name,
|
|
const char *value);
|
|
/*!
|
|
* \brief update the model in one round using dtrain
|
|
* \param handle handle
|
|
* \param iter current iteration rounds
|
|
* \param dtrain training data
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterUpdateOneIter(BoosterHandle handle,
|
|
int iter,
|
|
DMatrixHandle dtrain);
|
|
/*!
|
|
* \brief update the model, by directly specify gradient and second order gradient,
|
|
* this can be used to replace UpdateOneIter, to support customized loss function
|
|
* \param handle handle
|
|
* \param dtrain training data
|
|
* \param grad gradient statistics
|
|
* \param hess second order gradient statistics
|
|
* \param len length of grad/hess array
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterBoostOneIter(BoosterHandle handle,
|
|
DMatrixHandle dtrain,
|
|
float *grad,
|
|
float *hess,
|
|
bst_ulong len);
|
|
/*!
|
|
* \brief get evaluation statistics for xgboost
|
|
* \param handle handle
|
|
* \param iter current iteration rounds
|
|
* \param dmats pointers to data to be evaluated
|
|
* \param evnames pointers to names of each data
|
|
* \param len length of dmats
|
|
* \param out_result the string containing evaluation statistics
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterEvalOneIter(BoosterHandle handle,
|
|
int iter,
|
|
DMatrixHandle dmats[],
|
|
const char *evnames[],
|
|
bst_ulong len,
|
|
const char **out_result);
|
|
/*!
|
|
* \brief make prediction based on dmat
|
|
* \param handle handle
|
|
* \param dmat data matrix
|
|
* \param option_mask bit-mask of options taken in prediction, possible values
|
|
* 0:normal prediction
|
|
* 1:output margin instead of transformed value
|
|
* 2:output leaf index of trees instead of leaf value, note leaf index is unique per tree
|
|
* \param ntree_limit limit number of trees used for prediction, this is only valid for boosted trees
|
|
* when the parameter is set to 0, we will use all the trees
|
|
* \param out_len used to store length of returning result
|
|
* \param out_result used to set a pointer to array
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterPredict(BoosterHandle handle,
|
|
DMatrixHandle dmat,
|
|
int option_mask,
|
|
unsigned ntree_limit,
|
|
bst_ulong *out_len,
|
|
const float **out_result);
|
|
/*!
|
|
* \brief load model from existing file
|
|
* \param handle handle
|
|
* \param fname file name
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterLoadModel(BoosterHandle handle,
|
|
const char *fname);
|
|
/*!
|
|
* \brief save model into existing file
|
|
* \param handle handle
|
|
* \param fname file name
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterSaveModel(BoosterHandle handle,
|
|
const char *fname);
|
|
/*!
|
|
* \brief load model from in memory buffer
|
|
* \param handle handle
|
|
* \param buf pointer to the buffer
|
|
* \param len the length of the buffer
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterLoadModelFromBuffer(BoosterHandle handle,
|
|
const void *buf,
|
|
bst_ulong len);
|
|
/*!
|
|
* \brief save model into binary raw bytes, return header of the array
|
|
* user must copy the result out, before next xgboost call
|
|
* \param handle handle
|
|
* \param out_len the argument to hold the output length
|
|
* \param out_dptr the argument to hold the output data pointer
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterGetModelRaw(BoosterHandle handle,
|
|
bst_ulong *out_len,
|
|
const char **out_dptr);
|
|
/*!
|
|
* \brief dump model, return array of strings representing model dump
|
|
* \param handle handle
|
|
* \param fmap name to fmap can be empty string
|
|
* \param with_stats whether to dump with statistics
|
|
* \param out_len length of output array
|
|
* \param out_dump_array pointer to hold representing dump of each model
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterDumpModel(BoosterHandle handle,
|
|
const char *fmap,
|
|
int with_stats,
|
|
bst_ulong *out_len,
|
|
const char ***out_dump_array);
|
|
|
|
/*!
|
|
* \brief dump model, return array of strings representing model dump
|
|
* \param handle handle
|
|
* \param fnum number of features
|
|
* \param fnum names of features
|
|
* \param fnum types of features
|
|
* \param with_stats whether to dump with statistics
|
|
* \param out_len length of output array
|
|
* \param out_dump_array pointer to hold representing dump of each model
|
|
* \return 0 when success, -1 when failure happens
|
|
*/
|
|
XGB_DLL int XGBoosterDumpModelWithFeatures(BoosterHandle handle,
|
|
int fnum,
|
|
const char **fname,
|
|
const char **ftype,
|
|
int with_stats,
|
|
bst_ulong *len,
|
|
const char ***out_models);
|
|
|
|
#endif // XGBOOST_WRAPPER_H_
|