c_api.h 33.6 KB
Newer Older
Guolin Ke's avatar
Guolin Ke committed
1
2
#ifndef LIGHTGBM_C_API_H_
#define LIGHTGBM_C_API_H_
ww's avatar
ww committed
3
4
5

#include <LightGBM/meta.h>

6
7
8
#include <cstdint>
#include <exception>
#include <stdexcept>
wxchan's avatar
wxchan committed
9
#include <cstring>
10
#include <string>
wxchan's avatar
wxchan committed
11

12
13
14
/*!
* To avoid type conversion on large data, most of our expose interface support both for float_32 and float_64.
* Except following:
wxchan's avatar
wxchan committed
15
* 1. gradients and hessians.
16
* 2. Get current score for training data and validation
wxchan's avatar
wxchan committed
17
* The reason is because they are called frequently, the type-conversion on them maybe time cost.
18
19
*/

20
#include <LightGBM/export.h>
Guolin Ke's avatar
Guolin Ke committed
21

Guolin Ke's avatar
typo  
Guolin Ke committed
22
typedef void* DatasetHandle;
Guolin Ke's avatar
Guolin Ke committed
23
24
typedef void* BoosterHandle;

Guolin Ke's avatar
Guolin Ke committed
25
26
27
28
29
30
31
32
#define C_API_DTYPE_FLOAT32 (0)
#define C_API_DTYPE_FLOAT64 (1)
#define C_API_DTYPE_INT32   (2)
#define C_API_DTYPE_INT64   (3)

#define C_API_PREDICT_NORMAL     (0)
#define C_API_PREDICT_RAW_SCORE  (1)
#define C_API_PREDICT_LEAF_INDEX (2)
33
#define C_API_PREDICT_CONTRIB    (3)
34

Guolin Ke's avatar
Guolin Ke committed
35
36
/*!
* \brief get string message of the last error
wxchan's avatar
wxchan committed
37
*  all function in this file will return 0 when succeed
Guolin Ke's avatar
Guolin Ke committed
38
39
40
*  and -1 when an error occured,
* \return const char* error inforomation
*/
41
LIGHTGBM_C_EXPORT const char* LGBM_GetLastError();
Guolin Ke's avatar
Guolin Ke committed
42

Guolin Ke's avatar
Guolin Ke committed
43
// --- start Dataset interface
Guolin Ke's avatar
Guolin Ke committed
44
45
46
47

/*!
* \brief load data set from file like the command_line LightGBM do
* \param filename the name of the file
Guolin Ke's avatar
Guolin Ke committed
48
* \param parameters additional parameters
Guolin Ke's avatar
Guolin Ke committed
49
50
* \param reference used to align bin mapper with other dataset, nullptr means don't used
* \param out a loaded dataset
wxchan's avatar
wxchan committed
51
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
52
*/
53
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromFile(const char* filename,
54
55
56
                                                 const char* parameters,
                                                 const DatasetHandle reference,
                                                 DatasetHandle* out);
Guolin Ke's avatar
Guolin Ke committed
57

58
/*!
59
60
* \brief create a empty dataset by sampling data.
* \param sample_data sampled data, grouped by the column.
61
* \param sample_indices indices of sampled data.
62
* \param ncol number columns
63
64
* \param num_per_col Size of each sampling column
* \param num_sample_row Number of sampled rows
65
66
67
68
69
* \param num_total_row number of total rows
* \param parameters additional parameters
* \param out created dataset
* \return 0 when succeed, -1 when failure happens
*/
70
71
72
73
74
75
76
77
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromSampledColumn(double** sample_data,
                                                          int** sample_indices,
                                                          int32_t ncol,
                                                          const int* num_per_col,
                                                          int32_t num_sample_row,
                                                          int32_t num_total_row,
                                                          const char* parameters,
                                                          DatasetHandle* out);
Guolin Ke's avatar
Guolin Ke committed
78
79
80
81
82
83
84
85
86

/*!
* \brief create a empty dataset by reference Dataset
* \param reference used to align bin mapper
* \param num_total_row number of total rows
* \param out created dataset
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateByReference(const DatasetHandle reference,
87
88
                                                    int64_t num_total_row,
                                                    DatasetHandle* out);
Guolin Ke's avatar
Guolin Ke committed
89
90
91
92
93
94
95
96
97
98
99
100

/*!
* \brief push data to existing dataset, if nrow + start_row == num_total_row, will call dataset->FinishLoad
* \param dataset handle of dataset
* \param data pointer to the data space
* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
* \param nrow number of rows
* \param ncol number columns
* \param start_row row start index
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetPushRows(DatasetHandle dataset,
101
102
103
104
105
                                           const void* data,
                                           int data_type,
                                           int32_t nrow,
                                           int32_t ncol,
                                           int32_t start_row);
Guolin Ke's avatar
Guolin Ke committed
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121

/*!
* \brief push data to existing dataset, if nrow + start_row == num_total_row, will call dataset->FinishLoad
* \param dataset handle of dataset
* \param indptr pointer to row headers
* \param indptr_type type of indptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64
* \param indices findex
* \param data fvalue
* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
* \param nindptr number of rows in the matrix + 1
* \param nelem number of nonzero elements in the matrix
* \param num_col number of columns
* \param start_row row start index
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetPushRowsByCSR(DatasetHandle dataset,
122
123
124
125
126
127
128
129
130
                                                const void* indptr,
                                                int indptr_type,
                                                const int32_t* indices,
                                                const void* data,
                                                int data_type,
                                                int64_t nindptr,
                                                int64_t nelem,
                                                int64_t num_col,
                                                int64_t start_row);
Guolin Ke's avatar
Guolin Ke committed
131

Guolin Ke's avatar
Guolin Ke committed
132
133
134
/*!
* \brief create a dataset from CSR format
* \param indptr pointer to row headers
wxchan's avatar
wxchan committed
135
* \param indptr_type type of indptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64
Guolin Ke's avatar
Guolin Ke committed
136
137
* \param indices findex
* \param data fvalue
wxchan's avatar
wxchan committed
138
* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
Guolin Ke's avatar
Guolin Ke committed
139
* \param nindptr number of rows in the matrix + 1
Guolin Ke's avatar
Guolin Ke committed
140
* \param nelem number of nonzero elements in the matrix
wxchan's avatar
wxchan committed
141
* \param num_col number of columns
Guolin Ke's avatar
Guolin Ke committed
142
* \param parameters additional parameters
Guolin Ke's avatar
Guolin Ke committed
143
144
* \param reference used to align bin mapper with other dataset, nullptr means don't used
* \param out created dataset
wxchan's avatar
wxchan committed
145
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
146
*/
147
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromCSR(const void* indptr,
148
149
150
151
152
153
154
155
156
157
                                                int indptr_type,
                                                const int32_t* indices,
                                                const void* data,
                                                int data_type,
                                                int64_t nindptr,
                                                int64_t nelem,
                                                int64_t num_col,
                                                const char* parameters,
                                                const DatasetHandle reference,
                                                DatasetHandle* out);
Guolin Ke's avatar
Guolin Ke committed
158
159
160
161

/*!
* \brief create a dataset from CSC format
* \param col_ptr pointer to col headers
wxchan's avatar
wxchan committed
162
* \param col_ptr_type type of col_ptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64
Guolin Ke's avatar
Guolin Ke committed
163
164
* \param indices findex
* \param data fvalue
wxchan's avatar
wxchan committed
165
166
* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
* \param ncol_ptr number of cols in the matrix + 1
Guolin Ke's avatar
Guolin Ke committed
167
* \param nelem number of nonzero elements in the matrix
wxchan's avatar
wxchan committed
168
* \param num_row number of rows
Guolin Ke's avatar
Guolin Ke committed
169
170
171
* \param parameters additional parameters
* \param reference used to align bin mapper with other dataset, nullptr means don't used
* \param out created dataset
wxchan's avatar
wxchan committed
172
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
173
*/
174
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromCSC(const void* col_ptr,
175
176
177
178
179
180
181
182
183
184
                                                int col_ptr_type,
                                                const int32_t* indices,
                                                const void* data,
                                                int data_type,
                                                int64_t ncol_ptr,
                                                int64_t nelem,
                                                int64_t num_row,
                                                const char* parameters,
                                                const DatasetHandle reference,
                                                DatasetHandle* out);
Guolin Ke's avatar
Guolin Ke committed
185
186
187
188

/*!
* \brief create dataset from dense matrix
* \param data pointer to the data space
wxchan's avatar
wxchan committed
189
* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
Guolin Ke's avatar
Guolin Ke committed
190
191
* \param nrow number of rows
* \param ncol number columns
192
* \param is_row_major 1 for row major, 0 for column major
Guolin Ke's avatar
Guolin Ke committed
193
* \param parameters additional parameters
Guolin Ke's avatar
Guolin Ke committed
194
195
* \param reference used to align bin mapper with other dataset, nullptr means don't used
* \param out created dataset
wxchan's avatar
wxchan committed
196
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
197
*/
198
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromMat(const void* data,
199
200
201
202
203
204
205
                                                int data_type,
                                                int32_t nrow,
                                                int32_t ncol,
                                                int is_row_major,
                                                const char* parameters,
                                                const DatasetHandle reference,
                                                DatasetHandle* out);
Guolin Ke's avatar
Guolin Ke committed
206

207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
/*!
* \brief create dataset from array of dense matrices
* \param data pointer to the data space
* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
* \param nrow number of rows
* \param ncol number columns
* \param parameters additional parameters
* \param reference used to align bin mapper with other dataset, nullptr means don't used
* \param out created dataset
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromMats(int32_t nmat,
                                                 const void** data,
                                                 int data_type,
                                                 int32_t* nrow,
                                                 int32_t ncol,
                                                 int is_row_major,
                                                 const char* parameters,
                                                 const DatasetHandle reference,
                                                 DatasetHandle* out);

wxchan's avatar
wxchan committed
228
229
230
231
232
233
234
235
236
/*!
* \brief Create subset of a data
* \param handle handle of full dataset
* \param used_row_indices Indices used in subset
* \param num_used_row_indices len of used_row_indices
* \param parameters additional parameters
* \param out subset of data
* \return 0 when succeed, -1 when failure happens
*/
237
LIGHTGBM_C_EXPORT int LGBM_DatasetGetSubset(
238
  const DatasetHandle handle,
wxchan's avatar
wxchan committed
239
240
241
  const int32_t* used_row_indices,
  int32_t num_used_row_indices,
  const char* parameters,
Guolin Ke's avatar
typo  
Guolin Ke committed
242
  DatasetHandle* out);
wxchan's avatar
wxchan committed
243

Guolin Ke's avatar
Guolin Ke committed
244
245
246
247
248
249
250
/*!
* \brief save feature names to Dataset
* \param handle handle
* \param feature_names feature names
* \param num_feature_names number of feature names
* \return 0 when succeed, -1 when failure happens
*/
251
LIGHTGBM_C_EXPORT int LGBM_DatasetSetFeatureNames(
Guolin Ke's avatar
typo  
Guolin Ke committed
252
  DatasetHandle handle,
Guolin Ke's avatar
Guolin Ke committed
253
  const char** feature_names,
Guolin Ke's avatar
Guolin Ke committed
254
  int num_feature_names);
Guolin Ke's avatar
Guolin Ke committed
255

256
257
258
259
260
261
262
263

/*!
* \brief get feature names of Dataset
* \param handle handle
* \param feature_names feature names, should pre-allocate memory
* \param num_feature_names number of feature names
* \return 0 when succeed, -1 when failure happens
*/
264
LIGHTGBM_C_EXPORT int LGBM_DatasetGetFeatureNames(
265
266
  DatasetHandle handle,
  char** feature_names,
Guolin Ke's avatar
Guolin Ke committed
267
  int* num_feature_names);
268
269


Guolin Ke's avatar
Guolin Ke committed
270
271
/*!
* \brief free space for dataset
wxchan's avatar
wxchan committed
272
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
273
*/
274
LIGHTGBM_C_EXPORT int LGBM_DatasetFree(DatasetHandle handle);
Guolin Ke's avatar
Guolin Ke committed
275
276
277
278
279

/*!
* \brief save dateset to binary file
* \param handle a instance of dataset
* \param filename file name
wxchan's avatar
wxchan committed
280
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
281
*/
282
LIGHTGBM_C_EXPORT int LGBM_DatasetSaveBinary(DatasetHandle handle,
283
                                             const char* filename);
Guolin Ke's avatar
Guolin Ke committed
284
285
286

/*!
* \brief set vector to a content in info
wxchan's avatar
wxchan committed
287
288
*        Note: group and group only work for C_API_DTYPE_INT32
*              label and weight only work for C_API_DTYPE_FLOAT32
Guolin Ke's avatar
Guolin Ke committed
289
* \param handle a instance of dataset
wxchan's avatar
wxchan committed
290
* \param field_name field name, can be label, weight, group, group_id
291
* \param field_data pointer to vector
Guolin Ke's avatar
Guolin Ke committed
292
* \param num_element number of element in field_data
wxchan's avatar
wxchan committed
293
294
* \param type C_API_DTYPE_FLOAT32 or C_API_DTYPE_INT32
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
295
*/
296
LIGHTGBM_C_EXPORT int LGBM_DatasetSetField(DatasetHandle handle,
297
298
299
300
                                           const char* field_name,
                                           const void* field_data,
                                           int num_element,
                                           int type);
Guolin Ke's avatar
Guolin Ke committed
301
302

/*!
303
* \brief get info vector from dataset
Guolin Ke's avatar
Guolin Ke committed
304
305
306
307
* \param handle a instance of data matrix
* \param field_name field name
* \param out_len used to set result length
* \param out_ptr pointer to the result
wxchan's avatar
wxchan committed
308
309
* \param out_type  C_API_DTYPE_FLOAT32 or C_API_DTYPE_INT32
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
310
*/
311
LIGHTGBM_C_EXPORT int LGBM_DatasetGetField(DatasetHandle handle,
312
313
314
315
                                           const char* field_name,
                                           int* out_len,
                                           const void** out_ptr,
                                           int* out_type);
Guolin Ke's avatar
Guolin Ke committed
316
317
318
319
320

/*!
* \brief get number of data.
* \param handle the handle to the dataset
* \param out The address to hold number of data
wxchan's avatar
wxchan committed
321
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
322
*/
323
LIGHTGBM_C_EXPORT int LGBM_DatasetGetNumData(DatasetHandle handle,
324
                                             int* out);
Guolin Ke's avatar
Guolin Ke committed
325
326
327
328
329

/*!
* \brief get number of features
* \param handle the handle to the dataset
* \param out The output of number of features
wxchan's avatar
wxchan committed
330
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
331
*/
332
LIGHTGBM_C_EXPORT int LGBM_DatasetGetNumFeature(DatasetHandle handle,
333
                                                int* out);
Guolin Ke's avatar
Guolin Ke committed
334
335
336
337
338

// --- start Booster interfaces

/*!
* \brief create an new boosting learner
Guolin Ke's avatar
Guolin Ke committed
339
* \param train_data training data set
Guolin Ke's avatar
Guolin Ke committed
340
341
* \param parameters format: 'key1=value1 key2=value2'
* \prama out handle of created Booster
wxchan's avatar
wxchan committed
342
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
343
*/
344
LIGHTGBM_C_EXPORT int LGBM_BoosterCreate(const DatasetHandle train_data,
345
346
                                         const char* parameters,
                                         BoosterHandle* out);
Guolin Ke's avatar
Guolin Ke committed
347
348

/*!
Guolin Ke's avatar
Guolin Ke committed
349
* \brief load an existing boosting from model file
Guolin Ke's avatar
Guolin Ke committed
350
* \param filename filename of model
wxchan's avatar
wxchan committed
351
* \param out_num_iterations number of iterations of this booster
Guolin Ke's avatar
Guolin Ke committed
352
* \param out handle of created Booster
wxchan's avatar
wxchan committed
353
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
354
*/
355
LIGHTGBM_C_EXPORT int LGBM_BoosterCreateFromModelfile(
Guolin Ke's avatar
Guolin Ke committed
356
  const char* filename,
Guolin Ke's avatar
Guolin Ke committed
357
  int* out_num_iterations,
Guolin Ke's avatar
Guolin Ke committed
358
359
  BoosterHandle* out);

360
361
362
363
364
365
366
367
368
369
370
/*!
* \brief load an existing boosting from string
* \param model_str model string
* \param out_num_iterations number of iterations of this booster
* \param out handle of created Booster
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterLoadModelFromString(
  const char* model_str,
  int* out_num_iterations,
  BoosterHandle* out);
wxchan's avatar
wxchan committed
371

Guolin Ke's avatar
Guolin Ke committed
372
373
374
/*!
* \brief free obj in handle
* \param handle handle to be freed
wxchan's avatar
wxchan committed
375
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
376
*/
377
LIGHTGBM_C_EXPORT int LGBM_BoosterFree(BoosterHandle handle);
Guolin Ke's avatar
Guolin Ke committed
378

wxchan's avatar
wxchan committed
379
380
381
382
383
384
/*!
* \brief Merge model in two booster to first handle
* \param handle handle, will merge other handle to this
* \param other_handle
* \return 0 when succeed, -1 when failure happens
*/
385
LIGHTGBM_C_EXPORT int LGBM_BoosterMerge(BoosterHandle handle,
386
                                        BoosterHandle other_handle);
wxchan's avatar
wxchan committed
387
388
389
390
391
392
393

/*!
* \brief Add new validation to booster
* \param handle handle
* \param valid_data validation data set
* \return 0 when succeed, -1 when failure happens
*/
394
LIGHTGBM_C_EXPORT int LGBM_BoosterAddValidData(BoosterHandle handle,
395
                                               const DatasetHandle valid_data);
wxchan's avatar
wxchan committed
396
397
398
399
400
401
402

/*!
* \brief Reset training data for booster
* \param handle handle
* \param train_data training data set
* \return 0 when succeed, -1 when failure happens
*/
403
LIGHTGBM_C_EXPORT int LGBM_BoosterResetTrainingData(BoosterHandle handle,
404
                                                    const DatasetHandle train_data);
wxchan's avatar
wxchan committed
405
406
407
408
409
410
411

/*!
* \brief Reset config for current booster
* \param handle handle
* \param parameters format: 'key1=value1 key2=value2'
* \return 0 when succeed, -1 when failure happens
*/
412
LIGHTGBM_C_EXPORT int LGBM_BoosterResetParameter(BoosterHandle handle, const char* parameters);
wxchan's avatar
wxchan committed
413
414

/*!
Guolin Ke's avatar
Guolin Ke committed
415
* \brief Get number of class
wxchan's avatar
wxchan committed
416
417
418
419
* \param handle handle
* \param out_len number of class
* \return 0 when succeed, -1 when failure happens
*/
420
LIGHTGBM_C_EXPORT int LGBM_BoosterGetNumClasses(BoosterHandle handle, int* out_len);
wxchan's avatar
wxchan committed
421

Guolin Ke's avatar
Guolin Ke committed
422
423
424
/*!
* \brief update the model in one round
* \param handle handle
Guolin Ke's avatar
Guolin Ke committed
425
* \param is_finished 1 means finised(cannot split any more)
wxchan's avatar
wxchan committed
426
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
427
*/
428
LIGHTGBM_C_EXPORT int LGBM_BoosterUpdateOneIter(BoosterHandle handle, int* is_finished);
Guolin Ke's avatar
Guolin Ke committed
429
430
431
432
433
434
435

/*!
* \brief update the model, by directly specify gradient and second order gradient,
*       this can be used to support customized loss function
* \param handle handle
* \param grad gradient statistics
* \param hess second order gradient statistics
Guolin Ke's avatar
Guolin Ke committed
436
* \param is_finished 1 means finised(cannot split any more)
wxchan's avatar
wxchan committed
437
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
438
*/
439
LIGHTGBM_C_EXPORT int LGBM_BoosterUpdateOneIterCustom(BoosterHandle handle,
440
441
442
                                                      const float* grad,
                                                      const float* hess,
                                                      int* is_finished);
Guolin Ke's avatar
Guolin Ke committed
443
444

/*!
wxchan's avatar
wxchan committed
445
* \brief Rollback one iteration
Guolin Ke's avatar
Guolin Ke committed
446
* \param handle handle
wxchan's avatar
wxchan committed
447
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
448
*/
449
LIGHTGBM_C_EXPORT int LGBM_BoosterRollbackOneIter(BoosterHandle handle);
wxchan's avatar
wxchan committed
450
451
452
453
454
455

/*!
* \brief Get iteration of current boosting rounds
* \param out_iteration iteration of boosting rounds
* \return 0 when succeed, -1 when failure happens
*/
456
LIGHTGBM_C_EXPORT int LGBM_BoosterGetCurrentIteration(BoosterHandle handle, int* out_iteration);
Guolin Ke's avatar
Guolin Ke committed
457

Guolin Ke's avatar
Guolin Ke committed
458
/*!
Guolin Ke's avatar
Guolin Ke committed
459
* \brief Get number of eval
wxchan's avatar
wxchan committed
460
461
462
* \param out_len total number of eval results
* \return 0 when succeed, -1 when failure happens
*/
463
LIGHTGBM_C_EXPORT int LGBM_BoosterGetEvalCounts(BoosterHandle handle, int* out_len);
wxchan's avatar
wxchan committed
464
465

/*!
wxchan's avatar
wxchan committed
466
* \brief Get name of eval
wxchan's avatar
wxchan committed
467
* \param out_len total number of eval results
Guolin Ke's avatar
typo  
Guolin Ke committed
468
* \param out_strs names of eval result, need to pre-allocate memory before call this
wxchan's avatar
wxchan committed
469
470
* \return 0 when succeed, -1 when failure happens
*/
471
LIGHTGBM_C_EXPORT int LGBM_BoosterGetEvalNames(BoosterHandle handle, int* out_len, char** out_strs);
wxchan's avatar
wxchan committed
472

wxchan's avatar
wxchan committed
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
/*!
* \brief Get name of features
* \param out_len total number of features
* \param out_strs names of features, need to pre-allocate memory before call this
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetFeatureNames(BoosterHandle handle, int* out_len, char** out_strs);

/*!
* \brief Get number of features
* \param out_len total number of features
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetNumFeature(BoosterHandle handle, int* out_len);

wxchan's avatar
wxchan committed
488
489
/*!
* \brief get evaluation for training data and validation data
Guolin Ke's avatar
Guolin Ke committed
490
491
Note: 1. you should call LGBM_BoosterGetEvalNames first to get the name of evaluation results
2. should pre-allocate memory for out_results, you can get its length by LGBM_BoosterGetEvalCounts
Guolin Ke's avatar
Guolin Ke committed
492
* \param handle handle
wxchan's avatar
wxchan committed
493
* \param data_idx 0:training data, 1: 1st valid data, 2:2nd valid data ...
Guolin Ke's avatar
Guolin Ke committed
494
* \param out_len len of output result
wxchan's avatar
wxchan committed
495
496
* \param out_result float arrary contains result
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
497
*/
498
LIGHTGBM_C_EXPORT int LGBM_BoosterGetEval(BoosterHandle handle,
499
500
501
                                          int data_idx,
                                          int* out_len,
                                          double* out_results);
Guolin Ke's avatar
Guolin Ke committed
502
503
504
505
506
507
508
509
510
511

/*!
* \brief Get number of predict for inner dataset
this can be used to support customized eval function
Note:  should pre-allocate memory for out_result, its length is equal to num_class * num_data
* \param handle handle
* \param data_idx 0:training data, 1: 1st valid data, 2:2nd valid data ...
* \param out_len len of output result
* \return 0 when succeed, -1 when failure happens
*/
512
LIGHTGBM_C_EXPORT int LGBM_BoosterGetNumPredict(BoosterHandle handle,
513
514
                                                int data_idx,
                                                int64_t* out_len);
Guolin Ke's avatar
Guolin Ke committed
515

Guolin Ke's avatar
Guolin Ke committed
516
/*!
Guolin Ke's avatar
Guolin Ke committed
517
* \brief Get prediction for training data and validation data
Guolin Ke's avatar
Guolin Ke committed
518
519
this can be used to support customized eval function
Note:  should pre-allocate memory for out_result, its length is equal to num_class * num_data
Guolin Ke's avatar
Guolin Ke committed
520
* \param handle handle
wxchan's avatar
wxchan committed
521
* \param data_idx 0:training data, 1: 1st valid data, 2:2nd valid data ...
Guolin Ke's avatar
Guolin Ke committed
522
* \param out_len len of output result
Guolin Ke's avatar
Guolin Ke committed
523
* \param out_result used to set a pointer to array, should allocate memory before call this function
wxchan's avatar
wxchan committed
524
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
525
*/
526
LIGHTGBM_C_EXPORT int LGBM_BoosterGetPredict(BoosterHandle handle,
527
528
529
                                             int data_idx,
                                             int64_t* out_len,
                                             double* out_result);
Guolin Ke's avatar
Guolin Ke committed
530

531
532
533
534
/*!
* \brief make prediction for file
* \param handle handle
* \param data_filename filename of data file
wxchan's avatar
wxchan committed
535
536
537
538
539
540
* \param data_has_header data file has header or not
* \param predict_type
*          C_API_PREDICT_NORMAL: normal prediction, with transform (if needed)
*          C_API_PREDICT_RAW_SCORE: raw score
*          C_API_PREDICT_LEAF_INDEX: leaf index
* \param num_iteration number of iteration for prediction, <= 0 means no limit
Guolin Ke's avatar
Guolin Ke committed
541
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
542
* \param result_filename filename of result file
wxchan's avatar
wxchan committed
543
* \return 0 when succeed, -1 when failure happens
544
*/
545
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForFile(BoosterHandle handle,
546
547
548
549
                                                 const char* data_filename,
                                                 int data_has_header,
                                                 int predict_type,
                                                 int num_iteration,
550
                                                 const char* parameter,
551
                                                 const char* result_filename);
552

Guolin Ke's avatar
Guolin Ke committed
553
554
555
/*!
* \brief Get number of prediction
* \param handle handle
Guolin Ke's avatar
Guolin Ke committed
556
* \param num_row
Guolin Ke's avatar
Guolin Ke committed
557
558
559
560
561
* \param predict_type
*          C_API_PREDICT_NORMAL: normal prediction, with transform (if needed)
*          C_API_PREDICT_RAW_SCORE: raw score
*          C_API_PREDICT_LEAF_INDEX: leaf index
* \param num_iteration number of iteration for prediction, <= 0 means no limit
562
* \param out_len length of prediction
Guolin Ke's avatar
Guolin Ke committed
563
564
* \return 0 when succeed, -1 when failure happens
*/
565
LIGHTGBM_C_EXPORT int LGBM_BoosterCalcNumPredict(BoosterHandle handle,
566
567
568
569
                                                 int num_row,
                                                 int predict_type,
                                                 int num_iteration,
                                                 int64_t* out_len);
Guolin Ke's avatar
Guolin Ke committed
570

Guolin Ke's avatar
Guolin Ke committed
571
572
/*!
* \brief make prediction for an new data set
Guolin Ke's avatar
Guolin Ke committed
573
*        Note:  should pre-allocate memory for out_result,
wxchan's avatar
wxchan committed
574
575
*               for noraml and raw score: its length is equal to num_class * num_data
*               for leaf index, its length is equal to num_class * num_data * num_iteration
Guolin Ke's avatar
Guolin Ke committed
576
577
* \param handle handle
* \param indptr pointer to row headers
wxchan's avatar
wxchan committed
578
* \param indptr_type type of indptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64
Guolin Ke's avatar
Guolin Ke committed
579
580
* \param indices findex
* \param data fvalue
wxchan's avatar
wxchan committed
581
* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
Guolin Ke's avatar
Guolin Ke committed
582
* \param nindptr number of rows in the matrix + 1
Guolin Ke's avatar
Guolin Ke committed
583
584
585
* \param nelem number of nonzero elements in the matrix
* \param num_col number of columns; when it's set to 0, then guess from data
* \param predict_type
wxchan's avatar
wxchan committed
586
587
588
589
*          C_API_PREDICT_NORMAL: normal prediction, with transform (if needed)
*          C_API_PREDICT_RAW_SCORE: raw score
*          C_API_PREDICT_LEAF_INDEX: leaf index
* \param num_iteration number of iteration for prediction, <= 0 means no limit
Guolin Ke's avatar
Guolin Ke committed
590
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
wxchan's avatar
wxchan committed
591
* \param out_len len of output result
Guolin Ke's avatar
Guolin Ke committed
592
* \param out_result used to set a pointer to array, should allocate memory before call this function
wxchan's avatar
wxchan committed
593
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
594
*/
595
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForCSR(BoosterHandle handle,
596
597
598
599
600
601
602
603
604
605
                                                const void* indptr,
                                                int indptr_type,
                                                const int32_t* indices,
                                                const void* data,
                                                int data_type,
                                                int64_t nindptr,
                                                int64_t nelem,
                                                int64_t num_col,
                                                int predict_type,
                                                int num_iteration,
606
                                                const char* parameter,
607
608
                                                int64_t* out_len,
                                                double* out_result);
Guolin Ke's avatar
Guolin Ke committed
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628

/*!
* \brief make prediction for an new data set
*        Note:  should pre-allocate memory for out_result,
*               for noraml and raw score: its length is equal to num_class * num_data
*               for leaf index, its length is equal to num_class * num_data * num_iteration
* \param handle handle
* \param col_ptr pointer to col headers
* \param col_ptr_type type of col_ptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64
* \param indices findex
* \param data fvalue
* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
* \param ncol_ptr number of cols in the matrix + 1
* \param nelem number of nonzero elements in the matrix
* \param num_row number of rows
* \param predict_type
*          C_API_PREDICT_NORMAL: normal prediction, with transform (if needed)
*          C_API_PREDICT_RAW_SCORE: raw score
*          C_API_PREDICT_LEAF_INDEX: leaf index
* \param num_iteration number of iteration for prediction, <= 0 means no limit
Guolin Ke's avatar
Guolin Ke committed
629
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
Guolin Ke's avatar
Guolin Ke committed
630
631
632
633
* \param out_len len of output result
* \param out_result used to set a pointer to array, should allocate memory before call this function
* \return 0 when succeed, -1 when failure happens
*/
634
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForCSC(BoosterHandle handle,
635
636
637
638
639
640
641
642
643
644
                                                const void* col_ptr,
                                                int col_ptr_type,
                                                const int32_t* indices,
                                                const void* data,
                                                int data_type,
                                                int64_t ncol_ptr,
                                                int64_t nelem,
                                                int64_t num_row,
                                                int predict_type,
                                                int num_iteration,
645
                                                const char* parameter,
646
647
                                                int64_t* out_len,
                                                double* out_result);
Guolin Ke's avatar
Guolin Ke committed
648
649
650

/*!
* \brief make prediction for an new data set
wxchan's avatar
wxchan committed
651
652
653
*        Note:  should pre-allocate memory for out_result,
*               for noraml and raw score: its length is equal to num_class * num_data
*               for leaf index, its length is equal to num_class * num_data * num_iteration
Guolin Ke's avatar
Guolin Ke committed
654
655
* \param handle handle
* \param data pointer to the data space
wxchan's avatar
wxchan committed
656
* \param data_type type of data pointer, can be C_API_DTYPE_FLOAT32 or C_API_DTYPE_FLOAT64
Guolin Ke's avatar
Guolin Ke committed
657
658
* \param nrow number of rows
* \param ncol number columns
Guolin Ke's avatar
Guolin Ke committed
659
* \param is_row_major 1 for row major, 0 for column major
Guolin Ke's avatar
Guolin Ke committed
660
* \param predict_type
wxchan's avatar
wxchan committed
661
662
663
664
*          C_API_PREDICT_NORMAL: normal prediction, with transform (if needed)
*          C_API_PREDICT_RAW_SCORE: raw score
*          C_API_PREDICT_LEAF_INDEX: leaf index
* \param num_iteration number of iteration for prediction, <= 0 means no limit
Guolin Ke's avatar
Guolin Ke committed
665
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
wxchan's avatar
wxchan committed
666
* \param out_len len of output result
Guolin Ke's avatar
Guolin Ke committed
667
* \param out_result used to set a pointer to array, should allocate memory before call this function
wxchan's avatar
wxchan committed
668
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
669
*/
670
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForMat(BoosterHandle handle,
671
672
673
674
675
676
677
                                                const void* data,
                                                int data_type,
                                                int32_t nrow,
                                                int32_t ncol,
                                                int is_row_major,
                                                int predict_type,
                                                int num_iteration,
678
                                                const char* parameter,
679
680
                                                int64_t* out_len,
                                                double* out_result);
Guolin Ke's avatar
Guolin Ke committed
681
682
683
684

/*!
* \brief save model into file
* \param handle handle
wxchan's avatar
wxchan committed
685
* \param num_iteration, <= 0 means save all
Guolin Ke's avatar
Guolin Ke committed
686
* \param filename file name
wxchan's avatar
wxchan committed
687
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
688
*/
689
LIGHTGBM_C_EXPORT int LGBM_BoosterSaveModel(BoosterHandle handle,
690
691
                                            int num_iteration,
                                            const char* filename);
Guolin Ke's avatar
Guolin Ke committed
692

693
694
695
696
697
698
699
700
701
702
/*!
* \brief save model to string
* \param handle handle
* \param num_iteration, <= 0 means save all
* \param buffer_len string buffer length, if buffer_len < out_len, re-allocate buffer
* \param out_len actual output length
* \param out_str string of model, need to pre-allocate memory before call this
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterSaveModelToString(BoosterHandle handle,
703
                                                    int num_iteration,
704
705
                                                    int64_t buffer_len,
                                                    int64_t* out_len,
706
                                                    char* out_str);
707

wxchan's avatar
wxchan committed
708
709
710
/*!
* \brief dump model to json
* \param handle handle
711
* \param num_iteration, <= 0 means save all
wxchan's avatar
wxchan committed
712
713
* \param buffer_len string buffer length, if buffer_len < out_len, re-allocate buffer
* \param out_len actual output length
Guolin Ke's avatar
typo  
Guolin Ke committed
714
* \param out_str json format string of model, need to pre-allocate memory before call this
wxchan's avatar
wxchan committed
715
716
* \return 0 when succeed, -1 when failure happens
*/
717
LIGHTGBM_C_EXPORT int LGBM_BoosterDumpModel(BoosterHandle handle,
718
                                            int num_iteration,
719
720
                                            int64_t buffer_len,
                                            int64_t* out_len,
721
                                            char* out_str);
722

Guolin Ke's avatar
Guolin Ke committed
723
/*!
Guolin Ke's avatar
Guolin Ke committed
724
* \brief Get leaf value
Guolin Ke's avatar
Guolin Ke committed
725
726
727
728
729
730
* \param handle handle
* \param tree_idx index of tree
* \param leaf_idx index of leaf
* \param out_val out result
* \return 0 when succeed, -1 when failure happens
*/
731
LIGHTGBM_C_EXPORT int LGBM_BoosterGetLeafValue(BoosterHandle handle,
732
733
734
                                               int tree_idx,
                                               int leaf_idx,
                                               double* out_val);
Guolin Ke's avatar
Guolin Ke committed
735
736
737
738
739
740
741
742
743

/*!
* \brief Set leaf value
* \param handle handle
* \param tree_idx index of tree
* \param leaf_idx index of leaf
* \param val leaf value
* \return 0 when succeed, -1 when failure happens
*/
744
LIGHTGBM_C_EXPORT int LGBM_BoosterSetLeafValue(BoosterHandle handle,
745
746
747
                                               int tree_idx,
                                               int leaf_idx,
                                               double val);
748

749
750
751
752
753
754
755
756
757
758
759
760
761
/*!
* \brief get model feature importance
* \param handle handle
* \param num_iteration, <= 0 means use all
* \param importance_type: 0 for split, 1 for gain
* \param out_results output value array
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterFeatureImportance(BoosterHandle handle,
                                                    int num_iteration,
                                                    int importance_type,
                                                    double* out_results);

762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
/*!
* \brief Initilize the network
* \param machines represent the nodes, format: ip1:port1,ip2:port2
* \param local_listen_port
* \param listen_time_out
* \param num_machines
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_NetworkInit(const char* machines,
                                       int local_listen_port,
                                       int listen_time_out,
                                       int num_machines);

/*!
* \brief Finalize the network
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_NetworkFree();

781
782
783
LIGHTGBM_C_EXPORT int LGBM_NetworkInitWithFunctions(int num_machines, int rank, 
                                                    void* reduce_scatter_ext_fun, 
                                                    void* allgather_ext_fun);
784

785
// exception handle and error msg
786
static char* LastErrorMsg() { static THREAD_LOCAL char err_msg[512] = "Everything is fine"; return err_msg; }
787

788
#pragma warning(disable : 4996)
789
inline void LGBM_SetLastError(const char* msg) {
wxchan's avatar
wxchan committed
790
  std::strcpy(LastErrorMsg(), msg);
791
792
793
794
795
796
797
798
799
800
801
}

inline int LGBM_APIHandleException(const std::exception& ex) {
  LGBM_SetLastError(ex.what());
  return -1;
}
inline int LGBM_APIHandleException(const std::string& ex) {
  LGBM_SetLastError(ex.c_str());
  return -1;
}

802
#define API_BEGIN() try {
803
804
805
806
807

#define API_END() } \
catch(std::exception& ex) { return LGBM_APIHandleException(ex); } \
catch(std::string& ex) { return LGBM_APIHandleException(ex); } \
catch(...) { return LGBM_APIHandleException("unknown exception"); } \
wxchan's avatar
wxchan committed
808
return 0;
809

Guolin Ke's avatar
Guolin Ke committed
810
#endif // LIGHTGBM_C_API_H_