c_api.h 34.3 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
#include <cstdint>
wxchan's avatar
wxchan committed
5
6
#include <cstring>

7
8
9
/*!
* 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
10
* 1. gradients and hessians.
11
* 2. Get current score for training data and validation
wxchan's avatar
wxchan committed
12
* The reason is because they are called frequently, the type-conversion on them maybe time cost.
13
14
*/

15
#include <LightGBM/export.h>
Guolin Ke's avatar
Guolin Ke committed
16

Guolin Ke's avatar
typo  
Guolin Ke committed
17
typedef void* DatasetHandle;
Guolin Ke's avatar
Guolin Ke committed
18
19
typedef void* BoosterHandle;

Guolin Ke's avatar
Guolin Ke committed
20
21
22
23
24
25
26
27
#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)
28
#define C_API_PREDICT_CONTRIB    (3)
29

Guolin Ke's avatar
Guolin Ke committed
30
31
/*!
* \brief get string message of the last error
wxchan's avatar
wxchan committed
32
*  all function in this file will return 0 when succeed
Guolin Ke's avatar
Guolin Ke committed
33
34
35
*  and -1 when an error occured,
* \return const char* error inforomation
*/
36
LIGHTGBM_C_EXPORT const char* LGBM_GetLastError();
Guolin Ke's avatar
Guolin Ke committed
37

Guolin Ke's avatar
Guolin Ke committed
38
// --- start Dataset interface
Guolin Ke's avatar
Guolin Ke committed
39
40
41
42

/*!
* \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
43
* \param parameters additional parameters
Guolin Ke's avatar
Guolin Ke committed
44
45
* \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
46
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
47
*/
48
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromFile(const char* filename,
49
50
51
                                                 const char* parameters,
                                                 const DatasetHandle reference,
                                                 DatasetHandle* out);
Guolin Ke's avatar
Guolin Ke committed
52

53
/*!
54
55
* \brief create a empty dataset by sampling data.
* \param sample_data sampled data, grouped by the column.
56
* \param sample_indices indices of sampled data.
57
* \param ncol number columns
58
59
* \param num_per_col Size of each sampling column
* \param num_sample_row Number of sampled rows
60
61
62
63
64
* \param num_total_row number of total rows
* \param parameters additional parameters
* \param out created dataset
* \return 0 when succeed, -1 when failure happens
*/
65
66
67
68
69
70
71
72
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
73
74
75
76
77
78
79
80
81

/*!
* \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,
82
83
                                                    int64_t num_total_row,
                                                    DatasetHandle* out);
Guolin Ke's avatar
Guolin Ke committed
84
85
86
87
88
89
90
91
92
93
94
95

/*!
* \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,
96
97
98
99
100
                                           const void* data,
                                           int data_type,
                                           int32_t nrow,
                                           int32_t ncol,
                                           int32_t start_row);
Guolin Ke's avatar
Guolin Ke committed
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116

/*!
* \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,
117
118
119
120
121
122
123
124
125
                                                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
126

Guolin Ke's avatar
Guolin Ke committed
127
128
129
/*!
* \brief create a dataset from CSR format
* \param indptr pointer to row headers
wxchan's avatar
wxchan committed
130
* \param indptr_type type of indptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64
Guolin Ke's avatar
Guolin Ke committed
131
132
* \param indices findex
* \param data fvalue
wxchan's avatar
wxchan committed
133
* \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
134
* \param nindptr number of rows in the matrix + 1
Guolin Ke's avatar
Guolin Ke committed
135
* \param nelem number of nonzero elements in the matrix
wxchan's avatar
wxchan committed
136
* \param num_col number of columns
Guolin Ke's avatar
Guolin Ke committed
137
* \param parameters additional parameters
Guolin Ke's avatar
Guolin Ke committed
138
139
* \param reference used to align bin mapper with other dataset, nullptr means don't used
* \param out created dataset
wxchan's avatar
wxchan committed
140
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
141
*/
142
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromCSR(const void* indptr,
143
144
145
146
147
148
149
150
151
152
                                                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
153
154
155
156

/*!
* \brief create a dataset from CSC format
* \param col_ptr pointer to col headers
wxchan's avatar
wxchan committed
157
* \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
158
159
* \param indices findex
* \param data fvalue
wxchan's avatar
wxchan committed
160
161
* \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
162
* \param nelem number of nonzero elements in the matrix
wxchan's avatar
wxchan committed
163
* \param num_row number of rows
Guolin Ke's avatar
Guolin Ke committed
164
165
166
* \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
167
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
168
*/
169
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromCSC(const void* col_ptr,
170
171
172
173
174
175
176
177
178
179
                                                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
180
181
182
183

/*!
* \brief create dataset from dense matrix
* \param data pointer to the data space
wxchan's avatar
wxchan committed
184
* \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
185
186
* \param nrow number of rows
* \param ncol number columns
187
* \param is_row_major 1 for row major, 0 for column major
Guolin Ke's avatar
Guolin Ke committed
188
* \param parameters additional parameters
Guolin Ke's avatar
Guolin Ke committed
189
190
* \param reference used to align bin mapper with other dataset, nullptr means don't used
* \param out created dataset
wxchan's avatar
wxchan committed
191
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
192
*/
193
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromMat(const void* data,
194
195
196
197
198
199
200
                                                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
201

202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
/*!
* \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
223
224
225
226
227
228
229
230
231
/*!
* \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
*/
232
LIGHTGBM_C_EXPORT int LGBM_DatasetGetSubset(
233
  const DatasetHandle handle,
wxchan's avatar
wxchan committed
234
235
236
  const int32_t* used_row_indices,
  int32_t num_used_row_indices,
  const char* parameters,
Guolin Ke's avatar
typo  
Guolin Ke committed
237
  DatasetHandle* out);
wxchan's avatar
wxchan committed
238

Guolin Ke's avatar
Guolin Ke committed
239
240
241
242
243
244
245
/*!
* \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
*/
246
LIGHTGBM_C_EXPORT int LGBM_DatasetSetFeatureNames(
Guolin Ke's avatar
typo  
Guolin Ke committed
247
  DatasetHandle handle,
Guolin Ke's avatar
Guolin Ke committed
248
  const char** feature_names,
Guolin Ke's avatar
Guolin Ke committed
249
  int num_feature_names);
Guolin Ke's avatar
Guolin Ke committed
250

251
252
253
254
255
256
257
258

/*!
* \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
*/
259
LIGHTGBM_C_EXPORT int LGBM_DatasetGetFeatureNames(
260
261
  DatasetHandle handle,
  char** feature_names,
Guolin Ke's avatar
Guolin Ke committed
262
  int* num_feature_names);
263
264


Guolin Ke's avatar
Guolin Ke committed
265
266
/*!
* \brief free space for dataset
wxchan's avatar
wxchan committed
267
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
268
*/
269
LIGHTGBM_C_EXPORT int LGBM_DatasetFree(DatasetHandle handle);
Guolin Ke's avatar
Guolin Ke committed
270
271
272
273
274

/*!
* \brief save dateset to binary file
* \param handle a instance of dataset
* \param filename file name
wxchan's avatar
wxchan committed
275
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
276
*/
277
LIGHTGBM_C_EXPORT int LGBM_DatasetSaveBinary(DatasetHandle handle,
278
                                             const char* filename);
Guolin Ke's avatar
Guolin Ke committed
279
280
281

/*!
* \brief set vector to a content in info
wxchan's avatar
wxchan committed
282
283
*        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
284
* \param handle a instance of dataset
wxchan's avatar
wxchan committed
285
* \param field_name field name, can be label, weight, group, group_id
286
* \param field_data pointer to vector
Guolin Ke's avatar
Guolin Ke committed
287
* \param num_element number of element in field_data
wxchan's avatar
wxchan committed
288
289
* \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
290
*/
291
LIGHTGBM_C_EXPORT int LGBM_DatasetSetField(DatasetHandle handle,
292
293
294
295
                                           const char* field_name,
                                           const void* field_data,
                                           int num_element,
                                           int type);
Guolin Ke's avatar
Guolin Ke committed
296
297

/*!
298
* \brief get info vector from dataset
Guolin Ke's avatar
Guolin Ke committed
299
300
301
302
* \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
303
304
* \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
305
*/
306
LIGHTGBM_C_EXPORT int LGBM_DatasetGetField(DatasetHandle handle,
307
308
309
310
                                           const char* field_name,
                                           int* out_len,
                                           const void** out_ptr,
                                           int* out_type);
Guolin Ke's avatar
Guolin Ke committed
311
312
313
314
315

/*!
* \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
316
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
317
*/
318
LIGHTGBM_C_EXPORT int LGBM_DatasetGetNumData(DatasetHandle handle,
319
                                             int* out);
Guolin Ke's avatar
Guolin Ke committed
320
321
322
323
324

/*!
* \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
325
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
326
*/
327
LIGHTGBM_C_EXPORT int LGBM_DatasetGetNumFeature(DatasetHandle handle,
328
                                                int* out);
Guolin Ke's avatar
Guolin Ke committed
329
330
331
332
333

// --- start Booster interfaces

/*!
* \brief create an new boosting learner
Guolin Ke's avatar
Guolin Ke committed
334
* \param train_data training data set
Guolin Ke's avatar
Guolin Ke committed
335
336
* \param parameters format: 'key1=value1 key2=value2'
* \prama out handle of created Booster
wxchan's avatar
wxchan committed
337
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
338
*/
339
LIGHTGBM_C_EXPORT int LGBM_BoosterCreate(const DatasetHandle train_data,
340
341
                                         const char* parameters,
                                         BoosterHandle* out);
Guolin Ke's avatar
Guolin Ke committed
342
343

/*!
Guolin Ke's avatar
Guolin Ke committed
344
* \brief load an existing boosting from model file
Guolin Ke's avatar
Guolin Ke committed
345
* \param filename filename of model
wxchan's avatar
wxchan committed
346
* \param out_num_iterations number of iterations of this booster
Guolin Ke's avatar
Guolin Ke committed
347
* \param out handle of created Booster
wxchan's avatar
wxchan committed
348
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
349
*/
350
LIGHTGBM_C_EXPORT int LGBM_BoosterCreateFromModelfile(
Guolin Ke's avatar
Guolin Ke committed
351
  const char* filename,
Guolin Ke's avatar
Guolin Ke committed
352
  int* out_num_iterations,
Guolin Ke's avatar
Guolin Ke committed
353
354
  BoosterHandle* out);

355
356
357
358
359
360
361
362
363
364
365
/*!
* \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
366

Guolin Ke's avatar
Guolin Ke committed
367
368
369
/*!
* \brief free obj in handle
* \param handle handle to be freed
wxchan's avatar
wxchan committed
370
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
371
*/
372
LIGHTGBM_C_EXPORT int LGBM_BoosterFree(BoosterHandle handle);
Guolin Ke's avatar
Guolin Ke committed
373

374
375
376
/*!
* \brief Shuffle Models
*/
377
LIGHTGBM_C_EXPORT int LGBM_BoosterShuffleModels(BoosterHandle handle, int start_iter, int end_iter);
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

Guolin Ke's avatar
Guolin Ke committed
430
431
432
433
434
435
436
437
438
439
/*!
* \brief Refit the tree model using the new data (online learning)
* \param handle handle
* \param leaf_preds 
* \param nrow number of rows of leaf_preds
* \param ncol number of columns of leaf_preds
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterRefit(BoosterHandle handle, const int32_t* leaf_preds, int32_t nrow, int32_t ncol);

Guolin Ke's avatar
Guolin Ke committed
440
441
442
443
444
445
/*!
* \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
446
* \param is_finished 1 means finised(cannot split any more)
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_BoosterUpdateOneIterCustom(BoosterHandle handle,
450
451
452
                                                      const float* grad,
                                                      const float* hess,
                                                      int* is_finished);
Guolin Ke's avatar
Guolin Ke committed
453
454

/*!
wxchan's avatar
wxchan committed
455
* \brief Rollback one iteration
Guolin Ke's avatar
Guolin Ke committed
456
* \param handle handle
wxchan's avatar
wxchan committed
457
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
458
*/
459
LIGHTGBM_C_EXPORT int LGBM_BoosterRollbackOneIter(BoosterHandle handle);
wxchan's avatar
wxchan committed
460
461
462
463
464
465

/*!
* \brief Get iteration of current boosting rounds
* \param out_iteration iteration of boosting rounds
* \return 0 when succeed, -1 when failure happens
*/
466
LIGHTGBM_C_EXPORT int LGBM_BoosterGetCurrentIteration(BoosterHandle handle, int* out_iteration);
Guolin Ke's avatar
Guolin Ke committed
467

468
469
470
471
472
473
474
475
476
477
478
479
480
481
/*!
* \brief Get number of tree per iteration
* \param out_tree_per_iteration number of tree per iteration
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterNumModelPerIteration(BoosterHandle handle, int* out_tree_per_iteration);

/*!
* \brief Get number of weak sub-models
* \param out_models number of weak sub-models
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterNumberOfTotalModel(BoosterHandle handle, int* out_models);

Guolin Ke's avatar
Guolin Ke committed
482
/*!
Guolin Ke's avatar
Guolin Ke committed
483
* \brief Get number of eval
wxchan's avatar
wxchan committed
484
485
486
* \param out_len total number of eval results
* \return 0 when succeed, -1 when failure happens
*/
487
LIGHTGBM_C_EXPORT int LGBM_BoosterGetEvalCounts(BoosterHandle handle, int* out_len);
wxchan's avatar
wxchan committed
488
489

/*!
wxchan's avatar
wxchan committed
490
* \brief Get name of eval
wxchan's avatar
wxchan committed
491
* \param out_len total number of eval results
Guolin Ke's avatar
typo  
Guolin Ke committed
492
* \param out_strs names of eval result, need to pre-allocate memory before call this
wxchan's avatar
wxchan committed
493
494
* \return 0 when succeed, -1 when failure happens
*/
495
LIGHTGBM_C_EXPORT int LGBM_BoosterGetEvalNames(BoosterHandle handle, int* out_len, char** out_strs);
wxchan's avatar
wxchan committed
496

wxchan's avatar
wxchan committed
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
/*!
* \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
512
513
/*!
* \brief get evaluation for training data and validation data
Guolin Ke's avatar
Guolin Ke committed
514
515
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
516
* \param handle handle
wxchan's avatar
wxchan committed
517
* \param data_idx 0:training data, 1: 1st valid data, 2:2nd valid data ...
Guolin Ke's avatar
Guolin Ke committed
518
* \param out_len len of output result
wxchan's avatar
wxchan committed
519
520
* \param out_result float arrary contains result
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
521
*/
522
LIGHTGBM_C_EXPORT int LGBM_BoosterGetEval(BoosterHandle handle,
523
524
525
                                          int data_idx,
                                          int* out_len,
                                          double* out_results);
Guolin Ke's avatar
Guolin Ke committed
526
527
528
529
530
531
532
533
534
535

/*!
* \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
*/
536
LIGHTGBM_C_EXPORT int LGBM_BoosterGetNumPredict(BoosterHandle handle,
537
538
                                                int data_idx,
                                                int64_t* out_len);
Guolin Ke's avatar
Guolin Ke committed
539

Guolin Ke's avatar
Guolin Ke committed
540
/*!
Guolin Ke's avatar
Guolin Ke committed
541
* \brief Get prediction for training data and validation data
Guolin Ke's avatar
Guolin Ke committed
542
543
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
544
* \param handle handle
wxchan's avatar
wxchan committed
545
* \param data_idx 0:training data, 1: 1st valid data, 2:2nd valid data ...
Guolin Ke's avatar
Guolin Ke committed
546
* \param out_len len of output result
Guolin Ke's avatar
Guolin Ke committed
547
* \param out_result used to set a pointer to array, should allocate memory before call this function
wxchan's avatar
wxchan committed
548
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
549
*/
550
LIGHTGBM_C_EXPORT int LGBM_BoosterGetPredict(BoosterHandle handle,
551
552
553
                                             int data_idx,
                                             int64_t* out_len,
                                             double* out_result);
Guolin Ke's avatar
Guolin Ke committed
554

555
556
557
558
/*!
* \brief make prediction for file
* \param handle handle
* \param data_filename filename of data file
wxchan's avatar
wxchan committed
559
560
561
562
563
564
* \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
565
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
566
* \param result_filename filename of result file
wxchan's avatar
wxchan committed
567
* \return 0 when succeed, -1 when failure happens
568
*/
569
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForFile(BoosterHandle handle,
570
571
572
573
                                                 const char* data_filename,
                                                 int data_has_header,
                                                 int predict_type,
                                                 int num_iteration,
574
                                                 const char* parameter,
575
                                                 const char* result_filename);
576

Guolin Ke's avatar
Guolin Ke committed
577
578
579
/*!
* \brief Get number of prediction
* \param handle handle
Guolin Ke's avatar
Guolin Ke committed
580
* \param num_row
Guolin Ke's avatar
Guolin Ke committed
581
582
583
584
585
* \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
586
* \param out_len length of prediction
Guolin Ke's avatar
Guolin Ke committed
587
588
* \return 0 when succeed, -1 when failure happens
*/
589
LIGHTGBM_C_EXPORT int LGBM_BoosterCalcNumPredict(BoosterHandle handle,
590
591
592
593
                                                 int num_row,
                                                 int predict_type,
                                                 int num_iteration,
                                                 int64_t* out_len);
Guolin Ke's avatar
Guolin Ke committed
594

Guolin Ke's avatar
Guolin Ke committed
595
596
/*!
* \brief make prediction for an new data set
Guolin Ke's avatar
Guolin Ke committed
597
*        Note:  should pre-allocate memory for out_result,
wxchan's avatar
wxchan committed
598
599
*               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
600
601
* \param handle handle
* \param indptr pointer to row headers
wxchan's avatar
wxchan committed
602
* \param indptr_type type of indptr, can be C_API_DTYPE_INT32 or C_API_DTYPE_INT64
Guolin Ke's avatar
Guolin Ke committed
603
604
* \param indices findex
* \param data fvalue
wxchan's avatar
wxchan committed
605
* \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
606
* \param nindptr number of rows in the matrix + 1
Guolin Ke's avatar
Guolin Ke committed
607
608
609
* \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
610
611
612
613
*          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
614
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
wxchan's avatar
wxchan committed
615
* \param out_len len of output result
Guolin Ke's avatar
Guolin Ke committed
616
* \param out_result used to set a pointer to array, should allocate memory before call this function
wxchan's avatar
wxchan committed
617
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
618
*/
619
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForCSR(BoosterHandle handle,
620
621
622
623
624
625
626
627
628
629
                                                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,
630
                                                const char* parameter,
631
632
                                                int64_t* out_len,
                                                double* out_result);
Guolin Ke's avatar
Guolin Ke committed
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652

/*!
* \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
653
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
Guolin Ke's avatar
Guolin Ke committed
654
655
656
657
* \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
*/
658
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForCSC(BoosterHandle handle,
659
660
661
662
663
664
665
666
667
668
                                                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,
669
                                                const char* parameter,
670
671
                                                int64_t* out_len,
                                                double* out_result);
Guolin Ke's avatar
Guolin Ke committed
672
673
674

/*!
* \brief make prediction for an new data set
wxchan's avatar
wxchan committed
675
676
677
*        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
678
679
* \param handle handle
* \param data pointer to the data space
wxchan's avatar
wxchan committed
680
* \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
681
682
* \param nrow number of rows
* \param ncol number columns
Guolin Ke's avatar
Guolin Ke committed
683
* \param is_row_major 1 for row major, 0 for column major
Guolin Ke's avatar
Guolin Ke committed
684
* \param predict_type
wxchan's avatar
wxchan committed
685
686
687
688
*          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
689
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
wxchan's avatar
wxchan committed
690
* \param out_len len of output result
Guolin Ke's avatar
Guolin Ke committed
691
* \param out_result used to set a pointer to array, should allocate memory before call this function
wxchan's avatar
wxchan committed
692
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
693
*/
694
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForMat(BoosterHandle handle,
695
696
697
698
699
700
701
                                                const void* data,
                                                int data_type,
                                                int32_t nrow,
                                                int32_t ncol,
                                                int is_row_major,
                                                int predict_type,
                                                int num_iteration,
702
                                                const char* parameter,
703
704
                                                int64_t* out_len,
                                                double* out_result);
Guolin Ke's avatar
Guolin Ke committed
705
706
707
708

/*!
* \brief save model into file
* \param handle handle
wxchan's avatar
wxchan committed
709
* \param num_iteration, <= 0 means save all
Guolin Ke's avatar
Guolin Ke committed
710
* \param filename file name
wxchan's avatar
wxchan committed
711
* \return 0 when succeed, -1 when failure happens
Guolin Ke's avatar
Guolin Ke committed
712
*/
713
LIGHTGBM_C_EXPORT int LGBM_BoosterSaveModel(BoosterHandle handle,
714
                                            int start_iteration,
715
716
                                            int num_iteration,
                                            const char* filename);
Guolin Ke's avatar
Guolin Ke committed
717

718
719
720
721
722
723
724
725
726
727
/*!
* \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,
728
                                                    int start_iteration,
729
                                                    int num_iteration,
730
731
                                                    int64_t buffer_len,
                                                    int64_t* out_len,
732
                                                    char* out_str);
733

wxchan's avatar
wxchan committed
734
735
736
/*!
* \brief dump model to json
* \param handle handle
737
* \param num_iteration, <= 0 means save all
wxchan's avatar
wxchan committed
738
739
* \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
740
* \param out_str json format string of model, need to pre-allocate memory before call this
wxchan's avatar
wxchan committed
741
742
* \return 0 when succeed, -1 when failure happens
*/
743
LIGHTGBM_C_EXPORT int LGBM_BoosterDumpModel(BoosterHandle handle,
744
                                            int start_iteration,
745
                                            int num_iteration,
746
747
                                            int64_t buffer_len,
                                            int64_t* out_len,
748
                                            char* out_str);
749

Guolin Ke's avatar
Guolin Ke committed
750
/*!
Guolin Ke's avatar
Guolin Ke committed
751
* \brief Get leaf value
Guolin Ke's avatar
Guolin Ke committed
752
753
754
755
756
757
* \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
*/
758
LIGHTGBM_C_EXPORT int LGBM_BoosterGetLeafValue(BoosterHandle handle,
759
760
761
                                               int tree_idx,
                                               int leaf_idx,
                                               double* out_val);
Guolin Ke's avatar
Guolin Ke committed
762
763
764
765
766
767
768
769
770

/*!
* \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
*/
771
LIGHTGBM_C_EXPORT int LGBM_BoosterSetLeafValue(BoosterHandle handle,
772
773
774
                                               int tree_idx,
                                               int leaf_idx,
                                               double val);
775

776
777
778
779
780
781
782
783
784
785
786
787
788
/*!
* \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);

789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
/*!
* \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();

808
809
810
LIGHTGBM_C_EXPORT int LGBM_NetworkInitWithFunctions(int num_machines, int rank, 
                                                    void* reduce_scatter_ext_fun, 
                                                    void* allgather_ext_fun);
811

Guolin Ke's avatar
Guolin Ke committed
812
813
814
815
816
817

#if defined(_MSC_VER)
#define THREAD_LOCAL __declspec(thread) 
#else
#define THREAD_LOCAL thread_local
#endif
818
// exception handle and error msg
819
static char* LastErrorMsg() { static THREAD_LOCAL char err_msg[512] = "Everything is fine"; return err_msg; }
820

821
#pragma warning(disable : 4996)
822
inline void LGBM_SetLastError(const char* msg) {
wxchan's avatar
wxchan committed
823
  std::strcpy(LastErrorMsg(), msg);
824
825
}

Guolin Ke's avatar
Guolin Ke committed
826
#endif // LIGHTGBM_C_API_H_