-
Notifications
You must be signed in to change notification settings - Fork 3.8k
/
c_api.h
976 lines (894 loc) · 42.1 KB
/
c_api.h
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
#ifndef LIGHTGBM_C_API_H_
#define LIGHTGBM_C_API_H_
#include <cstdint>
#include <cstring>
/*!
* To avoid type conversion on large data, most of our expose interface support both for float_32 and float_64.
* Except following:
* 1. gradients and hessians.
* 2. Get current score for training data and validation
* The reason is because they are called frequently, the type-conversion on them maybe time cost.
*/
#include <LightGBM/export.h>
typedef void* DatasetHandle;
typedef void* BoosterHandle;
#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_DTYPE_INT8 (4)
#define C_API_PREDICT_NORMAL (0)
#define C_API_PREDICT_RAW_SCORE (1)
#define C_API_PREDICT_LEAF_INDEX (2)
#define C_API_PREDICT_CONTRIB (3)
/*!
* \brief get string message of the last error
* all function in this file will return 0 when succeed
* and -1 when an error occured,
* \return const char* error inforomation
*/
LIGHTGBM_C_EXPORT const char* LGBM_GetLastError();
// --- start Dataset interface
/*!
* \brief load data set from file like the command_line LightGBM do
* \param filename the name of the file
* \param parameters additional parameters
* \param reference used to align bin mapper with other dataset, nullptr means don't used
* \param out a loaded dataset
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetCreateFromFile(const char* filename,
const char* parameters,
const DatasetHandle reference,
DatasetHandle* out);
/*!
* \brief create a empty dataset by sampling data.
* \param sample_data sampled data, grouped by the column.
* \param sample_indices indices of sampled data.
* \param ncol number columns
* \param num_per_col Size of each sampling column
* \param num_sample_row Number of sampled rows
* \param num_total_row number of total rows
* \param parameters additional parameters
* \param out created dataset
* \return 0 when succeed, -1 when failure happens
*/
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);
/*!
* \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,
int64_t num_total_row,
DatasetHandle* out);
/*!
* \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,
const void* data,
int data_type,
int32_t nrow,
int32_t ncol,
int32_t start_row);
/*!
* \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,
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);
/*!
* \brief create a dataset from CSR format
* \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 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_DatasetCreateFromCSR(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,
const char* parameters,
const DatasetHandle reference,
DatasetHandle* out);
/*!
* \brief create a dataset from CSR format through callbacks
* \param get_row_funptr pointer to std::function<void(int idx, std::vector<std::pair<int, double>>& ret). CAlled for every row and expected to clear and fill ret
* \param num_rows number of rows
* \param num_col number of 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_DatasetCreateFromCSRFunc(void* get_row_funptr,
int num_rows,
int64_t num_col,
const char* parameters,
const DatasetHandle reference,
DatasetHandle* out);
/*!
* \brief create a dataset from CSC format
* \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 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_DatasetCreateFromCSC(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,
const char* parameters,
const DatasetHandle reference,
DatasetHandle* out);
/*!
* \brief create dataset from dense matrix
* \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 is_row_major 1 for row major, 0 for column major
* \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_DatasetCreateFromMat(const void* data,
int data_type,
int32_t nrow,
int32_t ncol,
int is_row_major,
const char* parameters,
const DatasetHandle reference,
DatasetHandle* out);
/*!
* \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);
/*!
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetGetSubset(
const DatasetHandle handle,
const int32_t* used_row_indices,
int32_t num_used_row_indices,
const char* parameters,
DatasetHandle* out);
/*!
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetSetFeatureNames(
DatasetHandle handle,
const char** feature_names,
int num_feature_names);
/*!
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetGetFeatureNames(
DatasetHandle handle,
char** feature_names,
int* num_feature_names);
/*!
* \brief free space for dataset
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetFree(DatasetHandle handle);
/*!
* \brief save dataset to binary file
* \param handle a instance of dataset
* \param filename file name
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetSaveBinary(DatasetHandle handle,
const char* filename);
/*!
* \brief save dataset to text file, intended for debugging use only
* \param handle a instance of dataset
* \param filename file name
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetDumpText(DatasetHandle handle,
const char* filename);
/*!
* \brief set vector to a content in info
* Note: group and group only work for C_API_DTYPE_INT32
* label and weight only work for C_API_DTYPE_FLOAT32
* \param handle a instance of dataset
* \param field_name field name, can be label, weight, group, group_id
* \param field_data pointer to vector
* \param num_element number of element in field_data
* \param type C_API_DTYPE_FLOAT32 or C_API_DTYPE_INT32
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetSetField(DatasetHandle handle,
const char* field_name,
const void* field_data,
int num_element,
int type);
/*!
* \brief get info vector from dataset
* \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
* \param out_type C_API_DTYPE_FLOAT32 or C_API_DTYPE_INT32
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetGetField(DatasetHandle handle,
const char* field_name,
int* out_len,
const void** out_ptr,
int* out_type);
/*!
* \brief Update parameters for a Dataset
* \param handle a instance of data matrix
* \param parameters parameters
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetUpdateParam(DatasetHandle handle, const char* parameters);
/*!
* \brief get number of data.
* \param handle the handle to the dataset
* \param out The address to hold number of data
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetGetNumData(DatasetHandle handle,
int* out);
/*!
* \brief get number of features
* \param handle the handle to the dataset
* \param out The output of number of features
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetGetNumFeature(DatasetHandle handle,
int* out);
/*!
* \brief Add features from source to target, then free source
* \param target The handle of the dataset to add features to
* \param source The handle of the dataset to take features from
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_DatasetAddFeaturesFrom(DatasetHandle target,
DatasetHandle source);
// --- start Booster interfaces
/*!
* \brief create an new boosting learner
* \param train_data training data set
* \param parameters format: 'key1=value1 key2=value2'
* \prama out handle of created Booster
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterCreate(const DatasetHandle train_data,
const char* parameters,
BoosterHandle* out);
/*!
* \brief load an existing boosting from model file
* \param filename filename of model
* \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_BoosterCreateFromModelfile(
const char* filename,
int* out_num_iterations,
BoosterHandle* out);
/*!
* \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);
/*!
* \brief free obj in handle
* \param handle handle to be freed
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterFree(BoosterHandle handle);
/*!
* \brief Shuffle Models
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterShuffleModels(BoosterHandle handle, int start_iter, int end_iter);
/*!
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterMerge(BoosterHandle handle,
BoosterHandle other_handle);
/*!
* \brief Add new validation to booster
* \param handle handle
* \param valid_data validation data set
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterAddValidData(BoosterHandle handle,
const DatasetHandle valid_data);
/*!
* \brief Reset training data for booster
* \param handle handle
* \param train_data training data set
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterResetTrainingData(BoosterHandle handle,
const DatasetHandle train_data);
/*!
* \brief Reset config for current booster
* \param handle handle
* \param parameters format: 'key1=value1 key2=value2'
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterResetParameter(BoosterHandle handle, const char* parameters);
/*!
* \brief Get number of class
* \param handle handle
* \param out_len number of class
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetNumClasses(BoosterHandle handle, int* out_len);
/*!
* \brief update the model in one round
* \param handle handle
* \param is_finished 1 means finised(cannot split any more)
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterUpdateOneIter(BoosterHandle handle, int* is_finished);
/*!
* \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);
/*!
* \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
* \param is_finished 1 means finised(cannot split any more)
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterUpdateOneIterCustom(BoosterHandle handle,
const float* grad,
const float* hess,
int* is_finished);
/*!
* \brief Rollback one iteration
* \param handle handle
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterRollbackOneIter(BoosterHandle handle);
/*!
* \brief Get iteration of current boosting rounds
* \param out_iteration iteration of boosting rounds
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetCurrentIteration(BoosterHandle handle, int* out_iteration);
/*!
* \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);
/*!
* \brief Get number of eval
* \param out_len total number of eval results
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetEvalCounts(BoosterHandle handle, int* out_len);
/*!
* \brief Get name of eval
* \param out_len total number of eval results
* \param out_strs names of eval result, need to pre-allocate memory before call this
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetEvalNames(BoosterHandle handle, int* out_len, char** out_strs);
/*!
* \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);
/*!
* \brief get evaluation for training data and validation data
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
* \param handle handle
* \param data_idx 0:training data, 1: 1st valid data, 2:2nd valid data ...
* \param out_len len of output result
* \param out_result float arrary contains result
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetEval(BoosterHandle handle,
int data_idx,
int* out_len,
double* out_results);
/*!
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetNumPredict(BoosterHandle handle,
int data_idx,
int64_t* out_len);
/*!
* \brief Get prediction for training data and validation data
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
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetPredict(BoosterHandle handle,
int data_idx,
int64_t* out_len,
double* out_result);
/*!
* \brief make prediction for file
* \param handle handle
* \param data_filename filename of data file
* \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
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
* \param result_filename filename of result file
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForFile(BoosterHandle handle,
const char* data_filename,
int data_has_header,
int predict_type,
int num_iteration,
const char* parameter,
const char* result_filename);
/*!
* \brief Get number of prediction
* \param handle handle
* \param num_row
* \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
* \param out_len length of prediction
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterCalcNumPredict(BoosterHandle handle,
int num_row,
int predict_type,
int num_iteration,
int64_t* out_len);
/*!
* \brief make prediction for an new data set
* Note: should pre-allocate memory for out_result,
* for normal 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 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; when it's set to 0, then guess from data
* \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
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForCSR(BoosterHandle handle,
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,
const char* parameter,
int64_t* out_len,
double* out_result);
/*!
* \brief make prediction for an new data set. This method re-uses the internal predictor structure
* from previous calls and is optimized for single row invocation.
* Note: should pre-allocate memory for out_result,
* for normal 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 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; when it's set to 0, then guess from data
* \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
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForCSRSingleRow(BoosterHandle handle,
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,
const char* parameter,
int64_t* out_len,
double* out_result);
/*!
* \brief make prediction for an new data set
* Note: should pre-allocate memory for out_result,
* for normal 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
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForCSC(BoosterHandle handle,
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,
const char* parameter,
int64_t* out_len,
double* out_result);
/*!
* \brief make prediction for an new data set
* Note: should pre-allocate memory for out_result,
* for normal 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 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 is_row_major 1 for row major, 0 for column major
* \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
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForMat(BoosterHandle handle,
const void* data,
int data_type,
int32_t nrow,
int32_t ncol,
int is_row_major,
int predict_type,
int num_iteration,
const char* parameter,
int64_t* out_len,
double* out_result);
/*!
* \brief make prediction for an new data set. This method re-uses the internal predictor structure
* from previous calls and is optimized for single row invocation.
* Note: should pre-allocate memory for out_result,
* for normal 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 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 is_row_major 1 for row major, 0 for column major
* \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
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
* \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
*/LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForMatSingleRow(BoosterHandle handle,
const void* data,
int data_type,
int ncol,
int is_row_major,
int predict_type,
int num_iteration,
const char* parameter,
int64_t* out_len,
double* out_result);
/*!
* \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 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 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
* \param parameter Other parameters for the parameters, e.g. early stopping for prediction.
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterPredictForMats(BoosterHandle handle,
const void** data,
int data_type,
int32_t nrow,
int32_t ncol,
int predict_type,
int num_iteration,
const char* parameter,
int64_t* out_len,
double* out_result);
/*!
* \brief save model into file
* \param handle handle
* \param num_iteration, <= 0 means save all
* \param filename file name
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterSaveModel(BoosterHandle handle,
int start_iteration,
int num_iteration,
const char* filename);
/*!
* \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,
int start_iteration,
int num_iteration,
int64_t buffer_len,
int64_t* out_len,
char* out_str);
/*!
* \brief dump model to json
* \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 json format string of model, need to pre-allocate memory before call this
* \return 0 when succeed, -1 when failure happens
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterDumpModel(BoosterHandle handle,
int start_iteration,
int num_iteration,
int64_t buffer_len,
int64_t* out_len,
char* out_str);
/*!
* \brief Get leaf value
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterGetLeafValue(BoosterHandle handle,
int tree_idx,
int leaf_idx,
double* out_val);
/*!
* \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
*/
LIGHTGBM_C_EXPORT int LGBM_BoosterSetLeafValue(BoosterHandle handle,
int tree_idx,
int leaf_idx,
double val);
/*!
* \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);
/*!
* \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();
LIGHTGBM_C_EXPORT int LGBM_NetworkInitWithFunctions(int num_machines, int rank,
void* reduce_scatter_ext_fun,
void* allgather_ext_fun);
#if defined(_MSC_VER)
#define THREAD_LOCAL __declspec(thread)
#else
#define THREAD_LOCAL thread_local
#endif
// exception handle and error msg
static char* LastErrorMsg() { static THREAD_LOCAL char err_msg[512] = "Everything is fine"; return err_msg; }
#pragma warning(disable : 4996)
inline void LGBM_SetLastError(const char* msg) {
std::strcpy(LastErrorMsg(), msg);
}
#endif // LIGHTGBM_C_API_H_