"python-package/vscode:/vscode.git/clone" did not exist on "f1f5ba15c27c795d0581b493082e96cb48ea9f34"
c_api.cpp 74.7 KB
Newer Older
1
2
3
4
/*!
 * Copyright (c) 2016 Microsoft Corporation. All rights reserved.
 * Licensed under the MIT License. See LICENSE file in the project root for license information.
 */
Guolin Ke's avatar
Guolin Ke committed
5
#include <LightGBM/c_api.h>
Guolin Ke's avatar
Guolin Ke committed
6

Guolin Ke's avatar
Guolin Ke committed
7
8
#include <LightGBM/boosting.h>
#include <LightGBM/config.h>
9
10
11
#include <LightGBM/dataset.h>
#include <LightGBM/dataset_loader.h>
#include <LightGBM/metric.h>
12
#include <LightGBM/network.h>
13
14
15
16
17
18
19
#include <LightGBM/objective_function.h>
#include <LightGBM/prediction_early_stop.h>
#include <LightGBM/utils/common.h>
#include <LightGBM/utils/log.h>
#include <LightGBM/utils/openmp_wrapper.h>
#include <LightGBM/utils/random.h>
#include <LightGBM/utils/threading.h>
Guolin Ke's avatar
Guolin Ke committed
20

21
22
23
24
25
26
27
28
#include <string>
#include <cstdio>
#include <functional>
#include <memory>
#include <mutex>
#include <stdexcept>
#include <vector>

29
#include "application/predictor.hpp"
Guolin Ke's avatar
Guolin Ke committed
30

Guolin Ke's avatar
Guolin Ke committed
31
32
namespace LightGBM {

Guolin Ke's avatar
Guolin Ke committed
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
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;
}

#define API_BEGIN() try {
#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"); } \
return 0;

49
50
51
52
53
54
55
56
const int PREDICTOR_TYPES = 4;

// Single row predictor to abstract away caching logic
class SingleRowPredictor {
 public:
  PredictFunction predict_function;
  int64_t num_pred_in_one_row;

Guolin Ke's avatar
Guolin Ke committed
57
  SingleRowPredictor(int predict_type, Boosting* boosting, const Config& config, int iter) {
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
    bool is_predict_leaf = false;
    bool is_raw_score = false;
    bool predict_contrib = false;
    if (predict_type == C_API_PREDICT_LEAF_INDEX) {
      is_predict_leaf = true;
    } else if (predict_type == C_API_PREDICT_RAW_SCORE) {
      is_raw_score = true;
    } else if (predict_type == C_API_PREDICT_CONTRIB) {
      predict_contrib = true;
    } else {
      is_raw_score = false;
    }
    early_stop_ = config.pred_early_stop;
    early_stop_freq_ = config.pred_early_stop_freq;
    early_stop_margin_ = config.pred_early_stop_margin;
    iter_ = iter;
Guolin Ke's avatar
Guolin Ke committed
74
    predictor_.reset(new Predictor(boosting, iter_, is_raw_score, is_predict_leaf, predict_contrib,
75
                                   early_stop_, early_stop_freq_, early_stop_margin_));
Guolin Ke's avatar
Guolin Ke committed
76
    num_pred_in_one_row = boosting->NumPredictOneRow(iter_, is_predict_leaf, predict_contrib);
77
    predict_function = predictor_->GetPredictFunction();
Guolin Ke's avatar
Guolin Ke committed
78
    num_total_model_ = boosting->NumberOfTotalModel();
79
  }
80

81
  ~SingleRowPredictor() {}
82

Guolin Ke's avatar
Guolin Ke committed
83
  bool IsPredictorEqual(const Config& config, int iter, Boosting* boosting) {
84
85
86
87
88
    return early_stop_ == config.pred_early_stop &&
      early_stop_freq_ == config.pred_early_stop_freq &&
      early_stop_margin_ == config.pred_early_stop_margin &&
      iter_ == iter &&
      num_total_model_ == boosting->NumberOfTotalModel();
89
  }
Guolin Ke's avatar
Guolin Ke committed
90

91
92
93
94
95
96
97
98
99
 private:
  std::unique_ptr<Predictor> predictor_;
  bool early_stop_;
  int early_stop_freq_;
  double early_stop_margin_;
  int iter_;
  int num_total_model_;
};

Guolin Ke's avatar
Guolin Ke committed
100
class Booster {
Nikita Titov's avatar
Nikita Titov committed
101
 public:
Guolin Ke's avatar
Guolin Ke committed
102
  explicit Booster(const char* filename) {
103
    boosting_.reset(Boosting::CreateBoosting("gbdt", filename));
104
105
  }

Guolin Ke's avatar
Guolin Ke committed
106
  Booster(const Dataset* train_data,
107
          const char* parameters) {
Guolin Ke's avatar
Guolin Ke committed
108
    auto param = Config::Str2Map(parameters);
wxchan's avatar
wxchan committed
109
    config_.Set(param);
110
111
112
    if (config_.num_threads > 0) {
      omp_set_num_threads(config_.num_threads);
    }
Guolin Ke's avatar
Guolin Ke committed
113
    // create boosting
Guolin Ke's avatar
Guolin Ke committed
114
    if (config_.input_model.size() > 0) {
115
116
      Log::Warning("Continued train from model is not supported for c_api,\n"
                   "please use continued train with input score");
Guolin Ke's avatar
Guolin Ke committed
117
    }
Guolin Ke's avatar
Guolin Ke committed
118

Guolin Ke's avatar
Guolin Ke committed
119
    boosting_.reset(Boosting::CreateBoosting(config_.boosting, nullptr));
Guolin Ke's avatar
Guolin Ke committed
120

121
122
    train_data_ = train_data;
    CreateObjectiveAndMetrics();
Guolin Ke's avatar
Guolin Ke committed
123
    // initialize the boosting
Guolin Ke's avatar
Guolin Ke committed
124
    if (config_.tree_learner == std::string("feature")) {
125
      Log::Fatal("Do not support feature parallel in c api");
126
    }
Guolin Ke's avatar
Guolin Ke committed
127
    if (Network::num_machines() == 1 && config_.tree_learner != std::string("serial")) {
128
      Log::Warning("Only find one worker, will switch to serial tree learner");
Guolin Ke's avatar
Guolin Ke committed
129
      config_.tree_learner = "serial";
130
    }
Guolin Ke's avatar
Guolin Ke committed
131
    boosting_->Init(&config_, train_data_, objective_fun_.get(),
132
                    Common::ConstPtrInVectorWrapper<Metric>(train_metric_));
wxchan's avatar
wxchan committed
133
134
135
136
137
  }

  void MergeFrom(const Booster* other) {
    std::lock_guard<std::mutex> lock(mutex_);
    boosting_->MergeFrom(other->boosting_.get());
Guolin Ke's avatar
Guolin Ke committed
138
139
140
141
  }

  ~Booster() {
  }
142

143
  void CreateObjectiveAndMetrics() {
Guolin Ke's avatar
Guolin Ke committed
144
    // create objective function
Guolin Ke's avatar
Guolin Ke committed
145
146
    objective_fun_.reset(ObjectiveFunction::CreateObjectiveFunction(config_.objective,
                                                                    config_));
Guolin Ke's avatar
Guolin Ke committed
147
148
149
150
151
152
153
154
155
156
    if (objective_fun_ == nullptr) {
      Log::Warning("Using self-defined objective function");
    }
    // initialize the objective function
    if (objective_fun_ != nullptr) {
      objective_fun_->Init(train_data_->metadata(), train_data_->num_data());
    }

    // create training metric
    train_metric_.clear();
Guolin Ke's avatar
Guolin Ke committed
157
    for (auto metric_type : config_.metric) {
Guolin Ke's avatar
Guolin Ke committed
158
      auto metric = std::unique_ptr<Metric>(
Guolin Ke's avatar
Guolin Ke committed
159
        Metric::CreateMetric(metric_type, config_));
Guolin Ke's avatar
Guolin Ke committed
160
161
162
163
164
      if (metric == nullptr) { continue; }
      metric->Init(train_data_->metadata(), train_data_->num_data());
      train_metric_.push_back(std::move(metric));
    }
    train_metric_.shrink_to_fit();
165
166
167
168
169
170
171
172
173
174
175
  }

  void ResetTrainingData(const Dataset* train_data) {
    if (train_data != train_data_) {
      std::lock_guard<std::mutex> lock(mutex_);
      train_data_ = train_data;
      CreateObjectiveAndMetrics();
      // reset the boosting
      boosting_->ResetTrainingData(train_data_,
                                   objective_fun_.get(), Common::ConstPtrInVectorWrapper<Metric>(train_metric_));
    }
wxchan's avatar
wxchan committed
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
  static void CheckDatasetResetConfig(
      const Config& old_config,
      const std::unordered_map<std::string, std::string>& new_param) {
    Config new_config;
    new_config.Set(new_param);
    if (new_param.count("data_random_seed") &&
        new_config.data_random_seed != old_config.data_random_seed) {
      Log::Fatal("Cannot change data_random_seed after constructed Dataset handle.");
    }
    if (new_param.count("max_bin") &&
        new_config.max_bin != old_config.max_bin) {
      Log::Fatal("Cannot change max_bin after constructed Dataset handle.");
    }
    if (new_param.count("max_bin_by_feature") &&
        new_config.max_bin_by_feature != old_config.max_bin_by_feature) {
      Log::Fatal(
          "Cannot change max_bin_by_feature after constructed Dataset handle.");
    }
    if (new_param.count("bin_construct_sample_cnt") &&
        new_config.bin_construct_sample_cnt !=
            old_config.bin_construct_sample_cnt) {
      Log::Fatal(
          "Cannot change bin_construct_sample_cnt after constructed Dataset "
          "handle.");
    }
    if (new_param.count("min_data_in_bin") &&
        new_config.min_data_in_bin != old_config.min_data_in_bin) {
      Log::Fatal(
          "Cannot change min_data_in_bin after constructed Dataset handle.");
    }
    if (new_param.count("use_missing") &&
        new_config.use_missing != old_config.use_missing) {
      Log::Fatal("Cannot change use_missing after constructed Dataset handle.");
    }
    if (new_param.count("zero_as_missing") &&
        new_config.zero_as_missing != old_config.zero_as_missing) {
      Log::Fatal(
          "Cannot change zero_as_missing after constructed Dataset handle.");
    }
    if (new_param.count("categorical_feature") &&
        new_config.categorical_feature != old_config.categorical_feature) {
      Log::Fatal(
          "Cannot change categorical_feature after constructed Dataset "
          "handle.");
    }
    if (new_param.count("feature_pre_filter") &&
        new_config.feature_pre_filter != old_config.feature_pre_filter) {
      Log::Fatal(
          "Cannot change feature_pre_filter after constructed Dataset handle.");
    }
    if (new_param.count("is_enable_sparse") &&
        new_config.is_enable_sparse != old_config.is_enable_sparse) {
      Log::Fatal(
          "Cannot change is_enable_sparse after constructed Dataset handle.");
    }
    if (new_param.count("pre_partition") &&
        new_config.pre_partition != old_config.pre_partition) {
      Log::Fatal(
          "Cannot change pre_partition after constructed Dataset handle.");
    }
    if (new_param.count("enable_bundle") &&
        new_config.enable_bundle != old_config.enable_bundle) {
      Log::Fatal(
          "Cannot change enable_bundle after constructed Dataset handle.");
    }
    if (new_param.count("header") && new_config.header != old_config.header) {
      Log::Fatal("Cannot change header after constructed Dataset handle.");
    }
    if (new_param.count("two_round") &&
        new_config.two_round != old_config.two_round) {
      Log::Fatal("Cannot change two_round after constructed Dataset handle.");
    }
    if (new_param.count("label_column") &&
        new_config.label_column != old_config.label_column) {
      Log::Fatal(
          "Cannot change label_column after constructed Dataset handle.");
    }
    if (new_param.count("weight_column") &&
        new_config.weight_column != old_config.weight_column) {
      Log::Fatal(
          "Cannot change weight_column after constructed Dataset handle.");
    }
    if (new_param.count("group_column") &&
        new_config.group_column != old_config.group_column) {
      Log::Fatal(
          "Cannot change group_column after constructed Dataset handle.");
    }
    if (new_param.count("ignore_column") &&
        new_config.ignore_column != old_config.ignore_column) {
      Log::Fatal(
          "Cannot change ignore_column after constructed Dataset handle.");
    }
    if (new_param.count("forcedbins_filename")) {
      Log::Fatal("Cannot change forced bins after constructed Dataset handle.");
    }
    if (new_param.count("min_data_in_leaf") &&
        new_config.min_data_in_leaf < old_config.min_data_in_leaf &&
        old_config.feature_pre_filter) {
      Log::Fatal(
          "Reducing `min_data_in_leaf` with `feature_pre_filter=true` may "
          "cause unexpected behaviour "
          "for features that were pre-filtered by the larger "
          "`min_data_in_leaf`.\n"
          "You need to set `feature_pre_filter=false` to dynamically change "
          "the `min_data_in_leaf`.");
    }
  }

wxchan's avatar
wxchan committed
286
  void ResetConfig(const char* parameters) {
Guolin Ke's avatar
Guolin Ke committed
287
    std::lock_guard<std::mutex> lock(mutex_);
Guolin Ke's avatar
Guolin Ke committed
288
    auto param = Config::Str2Map(parameters);
wxchan's avatar
wxchan committed
289
    if (param.count("num_class")) {
290
      Log::Fatal("Cannot change num_class during training");
wxchan's avatar
wxchan committed
291
    }
Guolin Ke's avatar
Guolin Ke committed
292
293
    if (param.count("boosting")) {
      Log::Fatal("Cannot change boosting during training");
wxchan's avatar
wxchan committed
294
    }
Guolin Ke's avatar
Guolin Ke committed
295
    if (param.count("metric")) {
296
      Log::Fatal("Cannot change metric during training");
Guolin Ke's avatar
Guolin Ke committed
297
    }
298
299
    CheckDatasetResetConfig(config_, param);

Guolin Ke's avatar
Guolin Ke committed
300
    config_.Set(param);
301

302
303
304
    if (config_.num_threads > 0) {
      omp_set_num_threads(config_.num_threads);
    }
Guolin Ke's avatar
Guolin Ke committed
305
306
307

    if (param.count("objective")) {
      // create objective function
Guolin Ke's avatar
Guolin Ke committed
308
309
      objective_fun_.reset(ObjectiveFunction::CreateObjectiveFunction(config_.objective,
                                                                      config_));
Guolin Ke's avatar
Guolin Ke committed
310
311
312
313
314
315
316
      if (objective_fun_ == nullptr) {
        Log::Warning("Using self-defined objective function");
      }
      // initialize the objective function
      if (objective_fun_ != nullptr) {
        objective_fun_->Init(train_data_->metadata(), train_data_->num_data());
      }
317
318
      boosting_->ResetTrainingData(train_data_,
                                   objective_fun_.get(), Common::ConstPtrInVectorWrapper<Metric>(train_metric_));
wxchan's avatar
wxchan committed
319
    }
Guolin Ke's avatar
Guolin Ke committed
320

Guolin Ke's avatar
Guolin Ke committed
321
    boosting_->ResetConfig(&config_);
wxchan's avatar
wxchan committed
322
323
324
325
326
  }

  void AddValidData(const Dataset* valid_data) {
    std::lock_guard<std::mutex> lock(mutex_);
    valid_metrics_.emplace_back();
Guolin Ke's avatar
Guolin Ke committed
327
328
    for (auto metric_type : config_.metric) {
      auto metric = std::unique_ptr<Metric>(Metric::CreateMetric(metric_type, config_));
wxchan's avatar
wxchan committed
329
330
331
332
333
334
      if (metric == nullptr) { continue; }
      metric->Init(valid_data->metadata(), valid_data->num_data());
      valid_metrics_.back().push_back(std::move(metric));
    }
    valid_metrics_.back().shrink_to_fit();
    boosting_->AddValidDataset(valid_data,
335
                               Common::ConstPtrInVectorWrapper<Metric>(valid_metrics_.back()));
wxchan's avatar
wxchan committed
336
  }
Guolin Ke's avatar
Guolin Ke committed
337

338
  bool TrainOneIter() {
wxchan's avatar
wxchan committed
339
    std::lock_guard<std::mutex> lock(mutex_);
Guolin Ke's avatar
Guolin Ke committed
340
    return boosting_->TrainOneIter(nullptr, nullptr);
341
342
  }

Guolin Ke's avatar
Guolin Ke committed
343
344
345
346
347
348
349
350
351
352
353
  void Refit(const int32_t* leaf_preds, int32_t nrow, int32_t ncol) {
    std::lock_guard<std::mutex> lock(mutex_);
    std::vector<std::vector<int32_t>> v_leaf_preds(nrow, std::vector<int32_t>(ncol, 0));
    for (int i = 0; i < nrow; ++i) {
      for (int j = 0; j < ncol; ++j) {
        v_leaf_preds[i][j] = leaf_preds[i * ncol + j];
      }
    }
    boosting_->RefitTree(v_leaf_preds);
  }

354
  bool TrainOneIter(const score_t* gradients, const score_t* hessians) {
wxchan's avatar
wxchan committed
355
    std::lock_guard<std::mutex> lock(mutex_);
Guolin Ke's avatar
Guolin Ke committed
356
    return boosting_->TrainOneIter(gradients, hessians);
357
358
  }

wxchan's avatar
wxchan committed
359
360
361
362
363
  void RollbackOneIter() {
    std::lock_guard<std::mutex> lock(mutex_);
    boosting_->RollbackOneIter();
  }

364
  void PredictSingleRow(int num_iteration, int predict_type, int ncol,
365
366
367
               std::function<std::vector<std::pair<int, double>>(int row_idx)> get_row_fun,
               const Config& config,
               double* out_result, int64_t* out_len) {
368
369
370
    if (!config.predict_disable_shape_check && ncol != boosting_->MaxFeatureIdx() + 1) {
      Log::Fatal("The number of features in data (%d) is not the same as it was in training data (%d).\n"\
                 "You can set ``predict_disable_shape_check=true`` to discard this error, but please be aware what you are doing.", ncol, boosting_->MaxFeatureIdx() + 1);
371
    }
372
    std::lock_guard<std::mutex> lock(mutex_);
373
    if (single_row_predictor_[predict_type].get() == nullptr ||
Guolin Ke's avatar
Guolin Ke committed
374
375
        !single_row_predictor_[predict_type]->IsPredictorEqual(config, num_iteration, boosting_.get())) {
      single_row_predictor_[predict_type].reset(new SingleRowPredictor(predict_type, boosting_.get(),
376
                                                                       config, num_iteration));
377
378
379
    }
    auto one_row = get_row_fun(0);
    auto pred_wrt_ptr = out_result;
380
    single_row_predictor_[predict_type]->predict_function(one_row, pred_wrt_ptr);
381

382
    *out_len = single_row_predictor_[predict_type]->num_pred_in_one_row;
383
384
385
  }


386
  void Predict(int num_iteration, int predict_type, int nrow, int ncol,
Guolin Ke's avatar
Guolin Ke committed
387
               std::function<std::vector<std::pair<int, double>>(int row_idx)> get_row_fun,
Guolin Ke's avatar
Guolin Ke committed
388
               const Config& config,
Guolin Ke's avatar
Guolin Ke committed
389
               double* out_result, int64_t* out_len) {
390
391
392
    if (!config.predict_disable_shape_check && ncol != boosting_->MaxFeatureIdx() + 1) {
      Log::Fatal("The number of features in data (%d) is not the same as it was in training data (%d).\n" \
                 "You can set ``predict_disable_shape_check=true`` to discard this error, but please be aware what you are doing.", ncol, boosting_->MaxFeatureIdx() + 1);
393
    }
wxchan's avatar
wxchan committed
394
    std::lock_guard<std::mutex> lock(mutex_);
Guolin Ke's avatar
Guolin Ke committed
395
396
    bool is_predict_leaf = false;
    bool is_raw_score = false;
Guolin Ke's avatar
Guolin Ke committed
397
    bool predict_contrib = false;
Guolin Ke's avatar
Guolin Ke committed
398
    if (predict_type == C_API_PREDICT_LEAF_INDEX) {
Guolin Ke's avatar
Guolin Ke committed
399
      is_predict_leaf = true;
Guolin Ke's avatar
Guolin Ke committed
400
    } else if (predict_type == C_API_PREDICT_RAW_SCORE) {
Guolin Ke's avatar
Guolin Ke committed
401
      is_raw_score = true;
402
    } else if (predict_type == C_API_PREDICT_CONTRIB) {
Guolin Ke's avatar
Guolin Ke committed
403
      predict_contrib = true;
Guolin Ke's avatar
Guolin Ke committed
404
405
    } else {
      is_raw_score = false;
Guolin Ke's avatar
Guolin Ke committed
406
    }
Guolin Ke's avatar
Guolin Ke committed
407

Guolin Ke's avatar
Guolin Ke committed
408
    Predictor predictor(boosting_.get(), num_iteration, is_raw_score, is_predict_leaf, predict_contrib,
409
                        config.pred_early_stop, config.pred_early_stop_freq, config.pred_early_stop_margin);
Guolin Ke's avatar
Guolin Ke committed
410
    int64_t num_pred_in_one_row = boosting_->NumPredictOneRow(num_iteration, is_predict_leaf, predict_contrib);
Guolin Ke's avatar
Guolin Ke committed
411
    auto pred_fun = predictor.GetPredictFunction();
412
413
    OMP_INIT_EX();
    #pragma omp parallel for schedule(static)
Guolin Ke's avatar
Guolin Ke committed
414
    for (int i = 0; i < nrow; ++i) {
415
      OMP_LOOP_EX_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
416
      auto one_row = get_row_fun(i);
Tony-Y's avatar
Tony-Y committed
417
      auto pred_wrt_ptr = out_result + static_cast<size_t>(num_pred_in_one_row) * i;
Guolin Ke's avatar
Guolin Ke committed
418
      pred_fun(one_row, pred_wrt_ptr);
419
      OMP_LOOP_EX_END();
Guolin Ke's avatar
Guolin Ke committed
420
    }
421
    OMP_THROW_EX();
422
    *out_len = num_pred_in_one_row * nrow;
Guolin Ke's avatar
Guolin Ke committed
423
424
425
  }

  void Predict(int num_iteration, int predict_type, const char* data_filename,
Guolin Ke's avatar
Guolin Ke committed
426
               int data_has_header, const Config& config,
cbecker's avatar
cbecker committed
427
               const char* result_filename) {
Guolin Ke's avatar
Guolin Ke committed
428
429
430
    std::lock_guard<std::mutex> lock(mutex_);
    bool is_predict_leaf = false;
    bool is_raw_score = false;
Guolin Ke's avatar
Guolin Ke committed
431
    bool predict_contrib = false;
Guolin Ke's avatar
Guolin Ke committed
432
433
434
435
    if (predict_type == C_API_PREDICT_LEAF_INDEX) {
      is_predict_leaf = true;
    } else if (predict_type == C_API_PREDICT_RAW_SCORE) {
      is_raw_score = true;
436
    } else if (predict_type == C_API_PREDICT_CONTRIB) {
Guolin Ke's avatar
Guolin Ke committed
437
      predict_contrib = true;
Guolin Ke's avatar
Guolin Ke committed
438
439
440
    } else {
      is_raw_score = false;
    }
Guolin Ke's avatar
Guolin Ke committed
441
    Predictor predictor(boosting_.get(), num_iteration, is_raw_score, is_predict_leaf, predict_contrib,
442
                        config.pred_early_stop, config.pred_early_stop_freq, config.pred_early_stop_margin);
Guolin Ke's avatar
Guolin Ke committed
443
    bool bool_data_has_header = data_has_header > 0 ? true : false;
444
    predictor.Predict(data_filename, result_filename, bool_data_has_header, config.predict_disable_shape_check);
Guolin Ke's avatar
Guolin Ke committed
445
446
  }

Guolin Ke's avatar
Guolin Ke committed
447
  void GetPredictAt(int data_idx, double* out_result, int64_t* out_len) {
wxchan's avatar
wxchan committed
448
449
450
    boosting_->GetPredictAt(data_idx, out_result, out_len);
  }

451
452
  void SaveModelToFile(int start_iteration, int num_iteration, const char* filename) {
    boosting_->SaveModelToFile(start_iteration, num_iteration, filename);
Guolin Ke's avatar
Guolin Ke committed
453
  }
454

455
  void LoadModelFromString(const char* model_str) {
456
457
    size_t len = std::strlen(model_str);
    boosting_->LoadModelFromString(model_str, len);
458
459
  }

460
461
  std::string SaveModelToString(int start_iteration, int num_iteration) {
    return boosting_->SaveModelToString(start_iteration, num_iteration);
462
463
  }

464
  std::string DumpModel(int start_iteration, int num_iteration) {
465
    return boosting_->DumpModel(start_iteration, num_iteration);
wxchan's avatar
wxchan committed
466
  }
467

468
469
470
471
  std::vector<double> FeatureImportance(int num_iteration, int importance_type) {
    return boosting_->FeatureImportance(num_iteration, importance_type);
  }

472
473
474
475
476
477
478
479
480
481
  double UpperBoundValue() const {
    std::lock_guard<std::mutex> lock(mutex_);
    return boosting_->GetUpperBoundValue();
  }

  double LowerBoundValue() const {
    std::lock_guard<std::mutex> lock(mutex_);
    return boosting_->GetLowerBoundValue();
  }

Guolin Ke's avatar
Guolin Ke committed
482
  double GetLeafValue(int tree_idx, int leaf_idx) const {
Guolin Ke's avatar
Guolin Ke committed
483
    return dynamic_cast<GBDTBase*>(boosting_.get())->GetLeafValue(tree_idx, leaf_idx);
Guolin Ke's avatar
Guolin Ke committed
484
485
486
487
  }

  void SetLeafValue(int tree_idx, int leaf_idx, double val) {
    std::lock_guard<std::mutex> lock(mutex_);
Guolin Ke's avatar
Guolin Ke committed
488
    dynamic_cast<GBDTBase*>(boosting_.get())->SetLeafValue(tree_idx, leaf_idx, val);
Guolin Ke's avatar
Guolin Ke committed
489
490
  }

491
  void ShuffleModels(int start_iter, int end_iter) {
492
    std::lock_guard<std::mutex> lock(mutex_);
493
    boosting_->ShuffleModels(start_iter, end_iter);
494
495
  }

wxchan's avatar
wxchan committed
496
497
498
499
500
501
502
  int GetEvalCounts() const {
    int ret = 0;
    for (const auto& metric : train_metric_) {
      ret += static_cast<int>(metric->GetName().size());
    }
    return ret;
  }
503

504
505
  int GetEvalNames(char** out_strs, const int len, const size_t buffer_len, size_t *out_buffer_len) const {
    *out_buffer_len = 0;
wxchan's avatar
wxchan committed
506
507
508
    int idx = 0;
    for (const auto& metric : train_metric_) {
      for (const auto& name : metric->GetName()) {
509
510
511
512
513
        if (idx < len) {
          std::memcpy(out_strs[idx], name.c_str(), std::min(name.size() + 1, buffer_len));
          out_strs[idx][buffer_len - 1] = '\0';
        }
        *out_buffer_len = std::max(name.size() + 1, *out_buffer_len);
wxchan's avatar
wxchan committed
514
515
516
517
518
519
        ++idx;
      }
    }
    return idx;
  }

520
521
  int GetFeatureNames(char** out_strs, const int len, const size_t buffer_len, size_t *out_buffer_len) const {
    *out_buffer_len = 0;
wxchan's avatar
wxchan committed
522
523
    int idx = 0;
    for (const auto& name : boosting_->FeatureNames()) {
524
525
526
527
528
      if (idx < len) {
        std::memcpy(out_strs[idx], name.c_str(), std::min(name.size() + 1, buffer_len));
        out_strs[idx][buffer_len - 1] = '\0';
      }
      *out_buffer_len = std::max(name.size() + 1, *out_buffer_len);
wxchan's avatar
wxchan committed
529
530
531
532
533
      ++idx;
    }
    return idx;
  }

wxchan's avatar
wxchan committed
534
  const Boosting* GetBoosting() const { return boosting_.get(); }
Guolin Ke's avatar
Guolin Ke committed
535

Nikita Titov's avatar
Nikita Titov committed
536
 private:
wxchan's avatar
wxchan committed
537
  const Dataset* train_data_;
Guolin Ke's avatar
Guolin Ke committed
538
  std::unique_ptr<Boosting> boosting_;
539
  std::unique_ptr<SingleRowPredictor> single_row_predictor_[PREDICTOR_TYPES];
540

Guolin Ke's avatar
Guolin Ke committed
541
  /*! \brief All configs */
Guolin Ke's avatar
Guolin Ke committed
542
  Config config_;
Guolin Ke's avatar
Guolin Ke committed
543
  /*! \brief Metric for training data */
Guolin Ke's avatar
Guolin Ke committed
544
  std::vector<std::unique_ptr<Metric>> train_metric_;
Guolin Ke's avatar
Guolin Ke committed
545
  /*! \brief Metrics for validation data */
Guolin Ke's avatar
Guolin Ke committed
546
  std::vector<std::vector<std::unique_ptr<Metric>>> valid_metrics_;
Guolin Ke's avatar
Guolin Ke committed
547
  /*! \brief Training objective function */
Guolin Ke's avatar
Guolin Ke committed
548
  std::unique_ptr<ObjectiveFunction> objective_fun_;
wxchan's avatar
wxchan committed
549
  /*! \brief mutex for threading safe call */
550
  mutable std::mutex mutex_;
Guolin Ke's avatar
Guolin Ke committed
551
552
};

553
}  // namespace LightGBM
Guolin Ke's avatar
Guolin Ke committed
554

555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
// explicitly declare symbols from LightGBM namespace
using LightGBM::AllgatherFunction;
using LightGBM::Booster;
using LightGBM::Common::CheckElementsIntervalClosed;
using LightGBM::Common::RemoveQuotationSymbol;
using LightGBM::Common::Vector2Ptr;
using LightGBM::Common::VectorSize;
using LightGBM::Config;
using LightGBM::data_size_t;
using LightGBM::Dataset;
using LightGBM::DatasetLoader;
using LightGBM::kZeroThreshold;
using LightGBM::LGBM_APIHandleException;
using LightGBM::Log;
using LightGBM::Network;
using LightGBM::Random;
using LightGBM::ReduceScatterFunction;
Guolin Ke's avatar
Guolin Ke committed
572

Guolin Ke's avatar
Guolin Ke committed
573
574
575
576
577
578
579
580
// some help functions used to convert data

std::function<std::vector<double>(int row_idx)>
RowFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_type, int is_row_major);

std::function<std::vector<std::pair<int, double>>(int row_idx)>
RowPairFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_type, int is_row_major);

581
582
583
std::function<std::vector<std::pair<int, double>>(int row_idx)>
RowPairFunctionFromDenseRows(const void** data, int num_col, int data_type);

Guolin Ke's avatar
Guolin Ke committed
584
585
std::function<std::vector<std::pair<int, double>>(int idx)>
RowFunctionFromCSR(const void* indptr, int indptr_type, const int32_t* indices,
586
                   const void* data, int data_type, int64_t nindptr, int64_t nelem);
Guolin Ke's avatar
Guolin Ke committed
587
588
589

// Row iterator of on column for CSC matrix
class CSC_RowIterator {
Nikita Titov's avatar
Nikita Titov committed
590
 public:
Guolin Ke's avatar
Guolin Ke committed
591
  CSC_RowIterator(const void* col_ptr, int col_ptr_type, const int32_t* indices,
592
                  const void* data, int data_type, int64_t ncol_ptr, int64_t nelem, int col_idx);
Guolin Ke's avatar
Guolin Ke committed
593
594
595
596
597
  ~CSC_RowIterator() {}
  // return value at idx, only can access by ascent order
  double Get(int idx);
  // return next non-zero pair, if index < 0, means no more data
  std::pair<int, double> NextNonZero();
Nikita Titov's avatar
Nikita Titov committed
598
599

 private:
Guolin Ke's avatar
Guolin Ke committed
600
601
602
603
604
605
606
607
608
  int nonzero_idx_ = 0;
  int cur_idx_ = -1;
  double cur_val_ = 0.0f;
  bool is_end_ = false;
  std::function<std::pair<int, double>(int idx)> iter_fun_;
};

// start of c_api functions

Guolin Ke's avatar
Guolin Ke committed
609
const char* LGBM_GetLastError() {
wxchan's avatar
wxchan committed
610
  return LastErrorMsg();
Guolin Ke's avatar
Guolin Ke committed
611
612
}

613
614
615
616
617
618
int LGBM_RegisterLogCallback(void (*callback)(const char*)) {
  API_BEGIN();
  Log::ResetCallBack(callback);
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
619
int LGBM_DatasetCreateFromFile(const char* filename,
620
621
622
                               const char* parameters,
                               const DatasetHandle reference,
                               DatasetHandle* out) {
623
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
624
625
  auto param = Config::Str2Map(parameters);
  Config config;
626
627
628
629
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
630
  DatasetLoader loader(config, nullptr, 1, filename);
Guolin Ke's avatar
Guolin Ke committed
631
  if (reference == nullptr) {
632
    if (Network::num_machines() == 1) {
633
      *out = loader.LoadFromFile(filename);
634
    } else {
635
      *out = loader.LoadFromFile(filename, Network::rank(), Network::num_machines());
636
    }
Guolin Ke's avatar
Guolin Ke committed
637
  } else {
638
    *out = loader.LoadFromFileAlignWithOtherDataset(filename,
639
                                                    reinterpret_cast<const Dataset*>(reference));
Guolin Ke's avatar
Guolin Ke committed
640
  }
641
  API_END();
Guolin Ke's avatar
Guolin Ke committed
642
643
}

644

Guolin Ke's avatar
Guolin Ke committed
645
int LGBM_DatasetCreateFromSampledColumn(double** sample_data,
646
647
648
649
650
651
652
                                        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) {
653
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
654
655
  auto param = Config::Str2Map(parameters);
  Config config;
656
657
658
659
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
Guolin Ke's avatar
Guolin Ke committed
660
  DatasetLoader loader(config, nullptr, 1, nullptr);
661
662
663
664
  *out = loader.CostructFromSampleData(sample_data, sample_indices, ncol, num_per_col,
                                       num_sample_row,
                                       static_cast<data_size_t>(num_total_row));
  API_END();
Guolin Ke's avatar
Guolin Ke committed
665
666
}

667

Guolin Ke's avatar
Guolin Ke committed
668
int LGBM_DatasetCreateByReference(const DatasetHandle reference,
669
670
                                  int64_t num_total_row,
                                  DatasetHandle* out) {
Guolin Ke's avatar
Guolin Ke committed
671
672
673
674
675
676
677
678
  API_BEGIN();
  std::unique_ptr<Dataset> ret;
  ret.reset(new Dataset(static_cast<data_size_t>(num_total_row)));
  ret->CreateValid(reinterpret_cast<const Dataset*>(reference));
  *out = ret.release();
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
679
int LGBM_DatasetPushRows(DatasetHandle dataset,
680
681
682
683
684
                         const void* data,
                         int data_type,
                         int32_t nrow,
                         int32_t ncol,
                         int32_t start_row) {
Guolin Ke's avatar
Guolin Ke committed
685
686
687
  API_BEGIN();
  auto p_dataset = reinterpret_cast<Dataset*>(dataset);
  auto get_row_fun = RowFunctionFromDenseMatric(data, nrow, ncol, data_type, 1);
688
  OMP_INIT_EX();
Guolin Ke's avatar
Guolin Ke committed
689
  #pragma omp parallel for schedule(static)
Guolin Ke's avatar
Guolin Ke committed
690
  for (int i = 0; i < nrow; ++i) {
691
    OMP_LOOP_EX_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
692
693
694
    const int tid = omp_get_thread_num();
    auto one_row = get_row_fun(i);
    p_dataset->PushOneRow(tid, start_row + i, one_row);
695
    OMP_LOOP_EX_END();
Guolin Ke's avatar
Guolin Ke committed
696
  }
697
  OMP_THROW_EX();
Guolin Ke's avatar
Guolin Ke committed
698
699
700
701
702
703
  if (start_row + nrow == p_dataset->num_data()) {
    p_dataset->FinishLoad();
  }
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
704
int LGBM_DatasetPushRowsByCSR(DatasetHandle dataset,
705
706
707
708
709
710
711
712
713
                              const void* indptr,
                              int indptr_type,
                              const int32_t* indices,
                              const void* data,
                              int data_type,
                              int64_t nindptr,
                              int64_t nelem,
                              int64_t,
                              int64_t start_row) {
Guolin Ke's avatar
Guolin Ke committed
714
715
716
717
  API_BEGIN();
  auto p_dataset = reinterpret_cast<Dataset*>(dataset);
  auto get_row_fun = RowFunctionFromCSR(indptr, indptr_type, indices, data, data_type, nindptr, nelem);
  int32_t nrow = static_cast<int32_t>(nindptr - 1);
718
  OMP_INIT_EX();
Guolin Ke's avatar
Guolin Ke committed
719
  #pragma omp parallel for schedule(static)
Guolin Ke's avatar
Guolin Ke committed
720
  for (int i = 0; i < nrow; ++i) {
721
    OMP_LOOP_EX_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
722
723
724
    const int tid = omp_get_thread_num();
    auto one_row = get_row_fun(i);
    p_dataset->PushOneRow(tid,
725
                          static_cast<data_size_t>(start_row + i), one_row);
726
    OMP_LOOP_EX_END();
Guolin Ke's avatar
Guolin Ke committed
727
  }
728
  OMP_THROW_EX();
Guolin Ke's avatar
Guolin Ke committed
729
730
731
732
733
734
  if (start_row + nrow == static_cast<int64_t>(p_dataset->num_data())) {
    p_dataset->FinishLoad();
  }
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
735
int LGBM_DatasetCreateFromMat(const void* data,
736
737
738
739
740
741
742
                              int data_type,
                              int32_t nrow,
                              int32_t ncol,
                              int is_row_major,
                              const char* parameters,
                              const DatasetHandle reference,
                              DatasetHandle* out) {
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
  return LGBM_DatasetCreateFromMats(1,
                                    &data,
                                    data_type,
                                    &nrow,
                                    ncol,
                                    is_row_major,
                                    parameters,
                                    reference,
                                    out);
}


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) {
764
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
765
766
  auto param = Config::Str2Map(parameters);
  Config config;
767
768
769
770
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
Guolin Ke's avatar
Guolin Ke committed
771
  std::unique_ptr<Dataset> ret;
772
773
774
775
776
777
778
779
780
  int32_t total_nrow = 0;
  for (int j = 0; j < nmat; ++j) {
    total_nrow += nrow[j];
  }

  std::vector<std::function<std::vector<double>(int row_idx)>> get_row_fun;
  for (int j = 0; j < nmat; ++j) {
    get_row_fun.push_back(RowFunctionFromDenseMatric(data[j], nrow[j], ncol, data_type, is_row_major));
  }
781

Guolin Ke's avatar
Guolin Ke committed
782
783
  if (reference == nullptr) {
    // sample data first
Guolin Ke's avatar
Guolin Ke committed
784
    Random rand(config.data_random_seed);
785
786
    int sample_cnt = static_cast<int>(total_nrow < config.bin_construct_sample_cnt ? total_nrow : config.bin_construct_sample_cnt);
    auto sample_indices = rand.Sample(total_nrow, sample_cnt);
787
    sample_cnt = static_cast<int>(sample_indices.size());
788
    std::vector<std::vector<double>> sample_values(ncol);
Guolin Ke's avatar
Guolin Ke committed
789
    std::vector<std::vector<int>> sample_idx(ncol);
790
791
792

    int offset = 0;
    int j = 0;
Guolin Ke's avatar
Guolin Ke committed
793
    for (size_t i = 0; i < sample_indices.size(); ++i) {
Guolin Ke's avatar
Guolin Ke committed
794
      auto idx = sample_indices[i];
795
796
797
798
      while ((idx - offset) >= nrow[j]) {
        offset += nrow[j];
        ++j;
      }
799

800
801
802
803
804
      auto row = get_row_fun[j](static_cast<int>(idx - offset));
      for (size_t k = 0; k < row.size(); ++k) {
        if (std::fabs(row[k]) > kZeroThreshold || std::isnan(row[k])) {
          sample_values[k].emplace_back(row[k]);
          sample_idx[k].emplace_back(static_cast<int>(i));
Guolin Ke's avatar
Guolin Ke committed
805
        }
Guolin Ke's avatar
Guolin Ke committed
806
807
      }
    }
Guolin Ke's avatar
Guolin Ke committed
808
    DatasetLoader loader(config, nullptr, 1, nullptr);
809
810
    ret.reset(loader.CostructFromSampleData(Vector2Ptr<double>(&sample_values).data(),
                                            Vector2Ptr<int>(&sample_idx).data(),
811
                                            ncol,
812
                                            VectorSize<double>(sample_values).data(),
813
                                            sample_cnt, total_nrow));
Guolin Ke's avatar
Guolin Ke committed
814
  } else {
815
    ret.reset(new Dataset(total_nrow));
Guolin Ke's avatar
Guolin Ke committed
816
    ret->CreateValid(
817
      reinterpret_cast<const Dataset*>(reference));
Guolin Ke's avatar
Guolin Ke committed
818
  }
819
820
821
822
823
824
825
826
827
828
829
830
831
832
  int32_t start_row = 0;
  for (int j = 0; j < nmat; ++j) {
    OMP_INIT_EX();
    #pragma omp parallel for schedule(static)
    for (int i = 0; i < nrow[j]; ++i) {
      OMP_LOOP_EX_BEGIN();
      const int tid = omp_get_thread_num();
      auto one_row = get_row_fun[j](i);
      ret->PushOneRow(tid, start_row + i, one_row);
      OMP_LOOP_EX_END();
    }
    OMP_THROW_EX();

    start_row += nrow[j];
Guolin Ke's avatar
Guolin Ke committed
833
834
  }
  ret->FinishLoad();
Guolin Ke's avatar
Guolin Ke committed
835
  *out = ret.release();
836
  API_END();
837
838
}

Guolin Ke's avatar
Guolin Ke committed
839
int LGBM_DatasetCreateFromCSR(const void* indptr,
840
841
842
843
844
845
846
847
848
849
                              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) {
850
  API_BEGIN();
851
852
853
854
855
  if (num_col <= 0) {
    Log::Fatal("The number of columns should be greater than zero.");
  } else if (num_col >= INT32_MAX) {
    Log::Fatal("The number of columns should be smaller than INT32_MAX.");
  }
Guolin Ke's avatar
Guolin Ke committed
856
857
  auto param = Config::Str2Map(parameters);
  Config config;
858
859
860
861
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
Guolin Ke's avatar
Guolin Ke committed
862
  std::unique_ptr<Dataset> ret;
863
  auto get_row_fun = RowFunctionFromCSR(indptr, indptr_type, indices, data, data_type, nindptr, nelem);
864
865
866
  int32_t nrow = static_cast<int32_t>(nindptr - 1);
  if (reference == nullptr) {
    // sample data first
Guolin Ke's avatar
Guolin Ke committed
867
868
    Random rand(config.data_random_seed);
    int sample_cnt = static_cast<int>(nrow < config.bin_construct_sample_cnt ? nrow : config.bin_construct_sample_cnt);
869
    auto sample_indices = rand.Sample(nrow, sample_cnt);
870
    sample_cnt = static_cast<int>(sample_indices.size());
Guolin Ke's avatar
Guolin Ke committed
871
872
    std::vector<std::vector<double>> sample_values(num_col);
    std::vector<std::vector<int>> sample_idx(num_col);
873
874
875
876
    for (size_t i = 0; i < sample_indices.size(); ++i) {
      auto idx = sample_indices[i];
      auto row = get_row_fun(static_cast<int>(idx));
      for (std::pair<int, double>& inner_data : row) {
Nikita Titov's avatar
Nikita Titov committed
877
        CHECK_LT(inner_data.first, num_col);
Guolin Ke's avatar
Guolin Ke committed
878
        if (std::fabs(inner_data.second) > kZeroThreshold || std::isnan(inner_data.second)) {
Guolin Ke's avatar
Guolin Ke committed
879
880
          sample_values[inner_data.first].emplace_back(inner_data.second);
          sample_idx[inner_data.first].emplace_back(static_cast<int>(i));
881
882
883
        }
      }
    }
Guolin Ke's avatar
Guolin Ke committed
884
    DatasetLoader loader(config, nullptr, 1, nullptr);
885
886
    ret.reset(loader.CostructFromSampleData(Vector2Ptr<double>(&sample_values).data(),
                                            Vector2Ptr<int>(&sample_idx).data(),
887
                                            static_cast<int>(num_col),
888
                                            VectorSize<double>(sample_values).data(),
889
                                            sample_cnt, nrow));
890
  } else {
891
    ret.reset(new Dataset(nrow));
Guolin Ke's avatar
Guolin Ke committed
892
    ret->CreateValid(
893
      reinterpret_cast<const Dataset*>(reference));
894
  }
895
  OMP_INIT_EX();
Guolin Ke's avatar
Guolin Ke committed
896
  #pragma omp parallel for schedule(static)
897
  for (int i = 0; i < nindptr - 1; ++i) {
898
    OMP_LOOP_EX_BEGIN();
899
900
901
    const int tid = omp_get_thread_num();
    auto one_row = get_row_fun(i);
    ret->PushOneRow(tid, i, one_row);
902
    OMP_LOOP_EX_END();
903
  }
904
  OMP_THROW_EX();
905
  ret->FinishLoad();
Guolin Ke's avatar
Guolin Ke committed
906
  *out = ret.release();
907
  API_END();
908
909
}

910
int LGBM_DatasetCreateFromCSRFunc(void* get_row_funptr,
911
912
913
914
915
                                  int num_rows,
                                  int64_t num_col,
                                  const char* parameters,
                                  const DatasetHandle reference,
                                  DatasetHandle* out) {
916
  API_BEGIN();
917
918
919
920
921
  if (num_col <= 0) {
    Log::Fatal("The number of columns should be greater than zero.");
  } else if (num_col >= INT32_MAX) {
    Log::Fatal("The number of columns should be smaller than INT32_MAX.");
  }
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
  auto get_row_fun = *static_cast<std::function<void(int idx, std::vector<std::pair<int, double>>&)>*>(get_row_funptr);
  auto param = Config::Str2Map(parameters);
  Config config;
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
  std::unique_ptr<Dataset> ret;
  int32_t nrow = num_rows;
  if (reference == nullptr) {
    // sample data first
    Random rand(config.data_random_seed);
    int sample_cnt = static_cast<int>(nrow < config.bin_construct_sample_cnt ? nrow : config.bin_construct_sample_cnt);
    auto sample_indices = rand.Sample(nrow, sample_cnt);
    sample_cnt = static_cast<int>(sample_indices.size());
    std::vector<std::vector<double>> sample_values(num_col);
    std::vector<std::vector<int>> sample_idx(num_col);
    // local buffer to re-use memory
    std::vector<std::pair<int, double>> buffer;
    for (size_t i = 0; i < sample_indices.size(); ++i) {
      auto idx = sample_indices[i];
      get_row_fun(static_cast<int>(idx), buffer);
      for (std::pair<int, double>& inner_data : buffer) {
Nikita Titov's avatar
Nikita Titov committed
945
        CHECK_LT(inner_data.first, num_col);
946
947
948
949
950
951
952
        if (std::fabs(inner_data.second) > kZeroThreshold || std::isnan(inner_data.second)) {
          sample_values[inner_data.first].emplace_back(inner_data.second);
          sample_idx[inner_data.first].emplace_back(static_cast<int>(i));
        }
      }
    }
    DatasetLoader loader(config, nullptr, 1, nullptr);
953
954
    ret.reset(loader.CostructFromSampleData(Vector2Ptr<double>(&sample_values).data(),
                                            Vector2Ptr<int>(&sample_idx).data(),
955
                                            static_cast<int>(num_col),
956
                                            VectorSize<double>(sample_values).data(),
957
958
959
960
961
962
                                            sample_cnt, nrow));
  } else {
    ret.reset(new Dataset(nrow));
    ret->CreateValid(
      reinterpret_cast<const Dataset*>(reference));
  }
963

964
  OMP_INIT_EX();
Guolin Ke's avatar
Guolin Ke committed
965
966
  std::vector<std::pair<int, double>> thread_buffer;
  #pragma omp parallel for schedule(static) private(thread_buffer)
967
968
969
  for (int i = 0; i < num_rows; ++i) {
    OMP_LOOP_EX_BEGIN();
    {
970
      const int tid = omp_get_thread_num();
Guolin Ke's avatar
Guolin Ke committed
971
972
      get_row_fun(i, thread_buffer);
      ret->PushOneRow(tid, i, thread_buffer);
973
974
975
976
977
978
979
980
981
    }
    OMP_LOOP_EX_END();
  }
  OMP_THROW_EX();
  ret->FinishLoad();
  *out = ret.release();
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
982
int LGBM_DatasetCreateFromCSC(const void* col_ptr,
983
984
985
986
987
988
989
990
991
992
                              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) {
993
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
994
995
  auto param = Config::Str2Map(parameters);
  Config config;
996
997
998
999
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
Guolin Ke's avatar
Guolin Ke committed
1000
  std::unique_ptr<Dataset> ret;
Guolin Ke's avatar
Guolin Ke committed
1001
1002
1003
  int32_t nrow = static_cast<int32_t>(num_row);
  if (reference == nullptr) {
    // sample data first
Guolin Ke's avatar
Guolin Ke committed
1004
1005
    Random rand(config.data_random_seed);
    int sample_cnt = static_cast<int>(nrow < config.bin_construct_sample_cnt ? nrow : config.bin_construct_sample_cnt);
Guolin Ke's avatar
Guolin Ke committed
1006
    auto sample_indices = rand.Sample(nrow, sample_cnt);
1007
    sample_cnt = static_cast<int>(sample_indices.size());
Guolin Ke's avatar
Guolin Ke committed
1008
    std::vector<std::vector<double>> sample_values(ncol_ptr - 1);
Guolin Ke's avatar
Guolin Ke committed
1009
    std::vector<std::vector<int>> sample_idx(ncol_ptr - 1);
1010
    OMP_INIT_EX();
Guolin Ke's avatar
Guolin Ke committed
1011
    #pragma omp parallel for schedule(static)
Guolin Ke's avatar
Guolin Ke committed
1012
    for (int i = 0; i < static_cast<int>(sample_values.size()); ++i) {
1013
      OMP_LOOP_EX_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1014
1015
1016
      CSC_RowIterator col_it(col_ptr, col_ptr_type, indices, data, data_type, ncol_ptr, nelem, i);
      for (int j = 0; j < sample_cnt; j++) {
        auto val = col_it.Get(sample_indices[j]);
Guolin Ke's avatar
Guolin Ke committed
1017
        if (std::fabs(val) > kZeroThreshold || std::isnan(val)) {
Guolin Ke's avatar
Guolin Ke committed
1018
1019
          sample_values[i].emplace_back(val);
          sample_idx[i].emplace_back(j);
Guolin Ke's avatar
Guolin Ke committed
1020
1021
        }
      }
1022
      OMP_LOOP_EX_END();
Guolin Ke's avatar
Guolin Ke committed
1023
    }
1024
    OMP_THROW_EX();
Guolin Ke's avatar
Guolin Ke committed
1025
    DatasetLoader loader(config, nullptr, 1, nullptr);
1026
1027
    ret.reset(loader.CostructFromSampleData(Vector2Ptr<double>(&sample_values).data(),
                                            Vector2Ptr<int>(&sample_idx).data(),
1028
                                            static_cast<int>(sample_values.size()),
1029
                                            VectorSize<double>(sample_values).data(),
1030
                                            sample_cnt, nrow));
Guolin Ke's avatar
Guolin Ke committed
1031
  } else {
1032
    ret.reset(new Dataset(nrow));
Guolin Ke's avatar
Guolin Ke committed
1033
    ret->CreateValid(
1034
      reinterpret_cast<const Dataset*>(reference));
Guolin Ke's avatar
Guolin Ke committed
1035
  }
1036
  OMP_INIT_EX();
Guolin Ke's avatar
Guolin Ke committed
1037
  #pragma omp parallel for schedule(static)
Guolin Ke's avatar
Guolin Ke committed
1038
  for (int i = 0; i < ncol_ptr - 1; ++i) {
1039
    OMP_LOOP_EX_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1040
    const int tid = omp_get_thread_num();
Guolin Ke's avatar
Guolin Ke committed
1041
    int feature_idx = ret->InnerFeatureIndex(i);
Guolin Ke's avatar
Guolin Ke committed
1042
    if (feature_idx < 0) { continue; }
Guolin Ke's avatar
Guolin Ke committed
1043
1044
    int group = ret->Feature2Group(feature_idx);
    int sub_feature = ret->Feture2SubFeature(feature_idx);
Guolin Ke's avatar
Guolin Ke committed
1045
    CSC_RowIterator col_it(col_ptr, col_ptr_type, indices, data, data_type, ncol_ptr, nelem, i);
Guolin Ke's avatar
Guolin Ke committed
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
    auto bin_mapper = ret->FeatureBinMapper(feature_idx);
    if (bin_mapper->GetDefaultBin() == bin_mapper->GetMostFreqBin()) {
      int row_idx = 0;
      while (row_idx < nrow) {
        auto pair = col_it.NextNonZero();
        row_idx = pair.first;
        // no more data
        if (row_idx < 0) { break; }
        ret->PushOneData(tid, row_idx, group, sub_feature, pair.second);
      }
    } else {
      for (int row_idx = 0; row_idx < nrow; ++row_idx) {
        auto val = col_it.Get(row_idx);
        ret->PushOneData(tid, row_idx, group, sub_feature, val);
      }
Guolin Ke's avatar
Guolin Ke committed
1061
    }
1062
    OMP_LOOP_EX_END();
Guolin Ke's avatar
Guolin Ke committed
1063
  }
1064
  OMP_THROW_EX();
Guolin Ke's avatar
Guolin Ke committed
1065
  ret->FinishLoad();
Guolin Ke's avatar
Guolin Ke committed
1066
  *out = ret.release();
1067
  API_END();
Guolin Ke's avatar
Guolin Ke committed
1068
1069
}

Guolin Ke's avatar
Guolin Ke committed
1070
int LGBM_DatasetGetSubset(
1071
  const DatasetHandle handle,
wxchan's avatar
wxchan committed
1072
1073
1074
  const int32_t* used_row_indices,
  int32_t num_used_row_indices,
  const char* parameters,
Guolin Ke's avatar
typo  
Guolin Ke committed
1075
  DatasetHandle* out) {
wxchan's avatar
wxchan committed
1076
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1077
1078
  auto param = Config::Str2Map(parameters);
  Config config;
1079
1080
1081
1082
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
1083
  auto full_dataset = reinterpret_cast<const Dataset*>(handle);
1084
  CHECK_GT(num_used_row_indices, 0);
1085
1086
  const int32_t lower = 0;
  const int32_t upper = full_dataset->num_data() - 1;
1087
  CheckElementsIntervalClosed(used_row_indices, lower, upper, num_used_row_indices, "Used indices of subset");
1088
1089
1090
  if (!std::is_sorted(used_row_indices, used_row_indices + num_used_row_indices)) {
    Log::Fatal("used_row_indices should be sorted in Subset");
  }
Guolin Ke's avatar
Guolin Ke committed
1091
  auto ret = std::unique_ptr<Dataset>(new Dataset(num_used_row_indices));
1092
  ret->CopyFeatureMapperFrom(full_dataset);
1093
  ret->CopySubrow(full_dataset, used_row_indices, num_used_row_indices, true);
wxchan's avatar
wxchan committed
1094
1095
1096
1097
  *out = ret.release();
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1098
int LGBM_DatasetSetFeatureNames(
Guolin Ke's avatar
typo  
Guolin Ke committed
1099
  DatasetHandle handle,
Guolin Ke's avatar
Guolin Ke committed
1100
  const char** feature_names,
Guolin Ke's avatar
Guolin Ke committed
1101
  int num_feature_names) {
Guolin Ke's avatar
Guolin Ke committed
1102
1103
1104
  API_BEGIN();
  auto dataset = reinterpret_cast<Dataset*>(handle);
  std::vector<std::string> feature_names_str;
Guolin Ke's avatar
Guolin Ke committed
1105
  for (int i = 0; i < num_feature_names; ++i) {
Guolin Ke's avatar
Guolin Ke committed
1106
1107
1108
1109
1110
1111
    feature_names_str.emplace_back(feature_names[i]);
  }
  dataset->set_feature_names(feature_names_str);
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1112
int LGBM_DatasetGetFeatureNames(
1113
1114
1115
1116
1117
1118
    DatasetHandle handle,
    const int len,
    int* num_feature_names,
    const size_t buffer_len,
    size_t* out_buffer_len,
    char** feature_names) {
1119
  API_BEGIN();
1120
  *out_buffer_len = 0;
1121
1122
  auto dataset = reinterpret_cast<Dataset*>(handle);
  auto inside_feature_name = dataset->feature_names();
Guolin Ke's avatar
Guolin Ke committed
1123
1124
  *num_feature_names = static_cast<int>(inside_feature_name.size());
  for (int i = 0; i < *num_feature_names; ++i) {
1125
1126
1127
1128
1129
    if (i < len) {
      std::memcpy(feature_names[i], inside_feature_name[i].c_str(), std::min(inside_feature_name[i].size() + 1, buffer_len));
      feature_names[i][buffer_len - 1] = '\0';
    }
    *out_buffer_len = std::max(inside_feature_name[i].size() + 1, *out_buffer_len);
1130
1131
1132
1133
  }
  API_END();
}

1134
1135
1136
#ifdef _MSC_VER
  #pragma warning(disable : 4702)
#endif
Guolin Ke's avatar
Guolin Ke committed
1137
int LGBM_DatasetFree(DatasetHandle handle) {
1138
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1139
  delete reinterpret_cast<Dataset*>(handle);
1140
  API_END();
1141
1142
}

Guolin Ke's avatar
Guolin Ke committed
1143
int LGBM_DatasetSaveBinary(DatasetHandle handle,
1144
                           const char* filename) {
1145
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1146
1147
  auto dataset = reinterpret_cast<Dataset*>(handle);
  dataset->SaveBinaryFile(filename);
1148
  API_END();
1149
1150
}

1151
1152
1153
1154
1155
1156
1157
1158
int LGBM_DatasetDumpText(DatasetHandle handle,
                         const char* filename) {
  API_BEGIN();
  auto dataset = reinterpret_cast<Dataset*>(handle);
  dataset->DumpTextFile(filename);
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1159
int LGBM_DatasetSetField(DatasetHandle handle,
1160
1161
1162
1163
                         const char* field_name,
                         const void* field_data,
                         int num_element,
                         int type) {
1164
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1165
  auto dataset = reinterpret_cast<Dataset*>(handle);
1166
  bool is_success = false;
Guolin Ke's avatar
Guolin Ke committed
1167
  if (type == C_API_DTYPE_FLOAT32) {
Guolin Ke's avatar
Guolin Ke committed
1168
    is_success = dataset->SetFloatField(field_name, reinterpret_cast<const float*>(field_data), static_cast<int32_t>(num_element));
Guolin Ke's avatar
Guolin Ke committed
1169
  } else if (type == C_API_DTYPE_INT32) {
Guolin Ke's avatar
Guolin Ke committed
1170
    is_success = dataset->SetIntField(field_name, reinterpret_cast<const int*>(field_data), static_cast<int32_t>(num_element));
Guolin Ke's avatar
Guolin Ke committed
1171
1172
  } else if (type == C_API_DTYPE_FLOAT64) {
    is_success = dataset->SetDoubleField(field_name, reinterpret_cast<const double*>(field_data), static_cast<int32_t>(num_element));
1173
  }
1174
  if (!is_success) { Log::Fatal("Input data type error or field not found"); }
1175
  API_END();
1176
1177
}

Guolin Ke's avatar
Guolin Ke committed
1178
int LGBM_DatasetGetField(DatasetHandle handle,
1179
1180
1181
1182
                         const char* field_name,
                         int* out_len,
                         const void** out_ptr,
                         int* out_type) {
1183
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1184
  auto dataset = reinterpret_cast<Dataset*>(handle);
1185
  bool is_success = false;
Guolin Ke's avatar
Guolin Ke committed
1186
  if (dataset->GetFloatField(field_name, out_len, reinterpret_cast<const float**>(out_ptr))) {
Guolin Ke's avatar
Guolin Ke committed
1187
    *out_type = C_API_DTYPE_FLOAT32;
1188
    is_success = true;
Guolin Ke's avatar
Guolin Ke committed
1189
  } else if (dataset->GetIntField(field_name, out_len, reinterpret_cast<const int**>(out_ptr))) {
Guolin Ke's avatar
Guolin Ke committed
1190
    *out_type = C_API_DTYPE_INT32;
1191
    is_success = true;
Guolin Ke's avatar
Guolin Ke committed
1192
1193
1194
  } else if (dataset->GetDoubleField(field_name, out_len, reinterpret_cast<const double**>(out_ptr))) {
    *out_type = C_API_DTYPE_FLOAT64;
    is_success = true;
Nikita Titov's avatar
Nikita Titov committed
1195
  }
1196
  if (!is_success) { Log::Fatal("Field not found"); }
wxchan's avatar
wxchan committed
1197
  if (*out_ptr == nullptr) { *out_len = 0; }
1198
  API_END();
1199
1200
}

1201
int LGBM_DatasetUpdateParamChecking(const char* old_parameters, const char* new_parameters) {
1202
  API_BEGIN();
1203
1204
1205
1206
1207
  auto old_param = Config::Str2Map(old_parameters);
  Config old_config;
  old_config.Set(old_param);
  auto new_param = Config::Str2Map(new_parameters);
  Booster::CheckDatasetResetConfig(old_config, new_param);
1208
1209
1210
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1211
int LGBM_DatasetGetNumData(DatasetHandle handle,
1212
                           int* out) {
1213
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1214
1215
  auto dataset = reinterpret_cast<Dataset*>(handle);
  *out = dataset->num_data();
1216
  API_END();
1217
1218
}

Guolin Ke's avatar
Guolin Ke committed
1219
int LGBM_DatasetGetNumFeature(DatasetHandle handle,
1220
                              int* out) {
1221
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1222
1223
  auto dataset = reinterpret_cast<Dataset*>(handle);
  *out = dataset->num_total_features();
1224
  API_END();
Guolin Ke's avatar
Guolin Ke committed
1225
}
1226

1227
1228
1229
1230
1231
int LGBM_DatasetAddFeaturesFrom(DatasetHandle target,
                                DatasetHandle source) {
  API_BEGIN();
  auto target_d = reinterpret_cast<Dataset*>(target);
  auto source_d = reinterpret_cast<Dataset*>(source);
1232
  target_d->AddFeaturesFrom(source_d);
1233
1234
1235
  API_END();
}

1236
1237
// ---- start of booster

Guolin Ke's avatar
Guolin Ke committed
1238
int LGBM_BoosterCreate(const DatasetHandle train_data,
1239
1240
                       const char* parameters,
                       BoosterHandle* out) {
1241
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1242
  const Dataset* p_train_data = reinterpret_cast<const Dataset*>(train_data);
wxchan's avatar
wxchan committed
1243
1244
  auto ret = std::unique_ptr<Booster>(new Booster(p_train_data, parameters));
  *out = ret.release();
1245
  API_END();
1246
1247
}

Guolin Ke's avatar
Guolin Ke committed
1248
int LGBM_BoosterCreateFromModelfile(
1249
  const char* filename,
Guolin Ke's avatar
Guolin Ke committed
1250
  int* out_num_iterations,
1251
  BoosterHandle* out) {
1252
  API_BEGIN();
wxchan's avatar
wxchan committed
1253
  auto ret = std::unique_ptr<Booster>(new Booster(filename));
Guolin Ke's avatar
Guolin Ke committed
1254
  *out_num_iterations = ret->GetBoosting()->GetCurrentIteration();
wxchan's avatar
wxchan committed
1255
  *out = ret.release();
1256
  API_END();
1257
1258
}

Guolin Ke's avatar
Guolin Ke committed
1259
int LGBM_BoosterLoadModelFromString(
1260
1261
1262
1263
  const char* model_str,
  int* out_num_iterations,
  BoosterHandle* out) {
  API_BEGIN();
wxchan's avatar
wxchan committed
1264
  auto ret = std::unique_ptr<Booster>(new Booster(nullptr));
1265
1266
1267
1268
1269
1270
  ret->LoadModelFromString(model_str);
  *out_num_iterations = ret->GetBoosting()->GetCurrentIteration();
  *out = ret.release();
  API_END();
}

1271
1272
1273
#ifdef _MSC_VER
  #pragma warning(disable : 4702)
#endif
Guolin Ke's avatar
Guolin Ke committed
1274
int LGBM_BoosterFree(BoosterHandle handle) {
1275
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1276
  delete reinterpret_cast<Booster*>(handle);
1277
  API_END();
1278
1279
}

1280
int LGBM_BoosterShuffleModels(BoosterHandle handle, int start_iter, int end_iter) {
1281
1282
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1283
  ref_booster->ShuffleModels(start_iter, end_iter);
1284
1285
1286
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1287
int LGBM_BoosterMerge(BoosterHandle handle,
1288
                      BoosterHandle other_handle) {
wxchan's avatar
wxchan committed
1289
1290
1291
1292
1293
1294
1295
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  Booster* ref_other_booster = reinterpret_cast<Booster*>(other_handle);
  ref_booster->MergeFrom(ref_other_booster);
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1296
int LGBM_BoosterAddValidData(BoosterHandle handle,
1297
                             const DatasetHandle valid_data) {
wxchan's avatar
wxchan committed
1298
1299
1300
1301
1302
1303
1304
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  const Dataset* p_dataset = reinterpret_cast<const Dataset*>(valid_data);
  ref_booster->AddValidData(p_dataset);
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1305
int LGBM_BoosterResetTrainingData(BoosterHandle handle,
1306
                                  const DatasetHandle train_data) {
wxchan's avatar
wxchan committed
1307
1308
1309
1310
1311
1312
1313
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  const Dataset* p_dataset = reinterpret_cast<const Dataset*>(train_data);
  ref_booster->ResetTrainingData(p_dataset);
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1314
int LGBM_BoosterResetParameter(BoosterHandle handle, const char* parameters) {
wxchan's avatar
wxchan committed
1315
1316
1317
1318
1319
1320
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  ref_booster->ResetConfig(parameters);
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1321
int LGBM_BoosterGetNumClasses(BoosterHandle handle, int* out_len) {
wxchan's avatar
wxchan committed
1322
1323
1324
1325
1326
1327
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  *out_len = ref_booster->GetBoosting()->NumberOfClasses();
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1328
1329
1330
1331
1332
1333
1334
int LGBM_BoosterRefit(BoosterHandle handle, const int32_t* leaf_preds, int32_t nrow, int32_t ncol) {
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  ref_booster->Refit(leaf_preds, nrow, ncol);
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1335
int LGBM_BoosterUpdateOneIter(BoosterHandle handle, int* is_finished) {
1336
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1337
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1338
1339
1340
1341
1342
  if (ref_booster->TrainOneIter()) {
    *is_finished = 1;
  } else {
    *is_finished = 0;
  }
1343
  API_END();
1344
1345
}

Guolin Ke's avatar
Guolin Ke committed
1346
int LGBM_BoosterUpdateOneIterCustom(BoosterHandle handle,
1347
1348
1349
                                    const float* grad,
                                    const float* hess,
                                    int* is_finished) {
1350
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1351
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1352
  #ifdef SCORE_T_USE_DOUBLE
1353
  Log::Fatal("Don't support custom loss function when SCORE_T_USE_DOUBLE is enabled");
1354
  #else
1355
1356
1357
1358
1359
  if (ref_booster->TrainOneIter(grad, hess)) {
    *is_finished = 1;
  } else {
    *is_finished = 0;
  }
1360
  #endif
1361
  API_END();
1362
1363
}

Guolin Ke's avatar
Guolin Ke committed
1364
int LGBM_BoosterRollbackOneIter(BoosterHandle handle) {
wxchan's avatar
wxchan committed
1365
1366
1367
1368
1369
1370
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  ref_booster->RollbackOneIter();
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1371
int LGBM_BoosterGetCurrentIteration(BoosterHandle handle, int* out_iteration) {
wxchan's avatar
wxchan committed
1372
1373
1374
1375
1376
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  *out_iteration = ref_booster->GetBoosting()->GetCurrentIteration();
  API_END();
}
Guolin Ke's avatar
Guolin Ke committed
1377

1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
int LGBM_BoosterNumModelPerIteration(BoosterHandle handle, int* out_tree_per_iteration) {
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  *out_tree_per_iteration = ref_booster->GetBoosting()->NumModelPerIteration();
  API_END();
}

int LGBM_BoosterNumberOfTotalModel(BoosterHandle handle, int* out_models) {
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  *out_models = ref_booster->GetBoosting()->NumberOfTotalModel();
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1392
int LGBM_BoosterGetEvalCounts(BoosterHandle handle, int* out_len) {
wxchan's avatar
wxchan committed
1393
1394
1395
1396
1397
1398
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  *out_len = ref_booster->GetEvalCounts();
  API_END();
}

1399
1400
1401
1402
1403
1404
int LGBM_BoosterGetEvalNames(BoosterHandle handle,
                             const int len,
                             int* out_len,
                             const size_t buffer_len,
                             size_t* out_buffer_len,
                             char** out_strs) {
wxchan's avatar
wxchan committed
1405
1406
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1407
  *out_len = ref_booster->GetEvalNames(out_strs, len, buffer_len, out_buffer_len);
wxchan's avatar
wxchan committed
1408
1409
1410
  API_END();
}

1411
1412
1413
1414
1415
1416
int LGBM_BoosterGetFeatureNames(BoosterHandle handle,
                                const int len,
                                int* out_len,
                                const size_t buffer_len,
                                size_t* out_buffer_len,
                                char** out_strs) {
wxchan's avatar
wxchan committed
1417
1418
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1419
  *out_len = ref_booster->GetFeatureNames(out_strs, len, buffer_len, out_buffer_len);
wxchan's avatar
wxchan committed
1420
1421
1422
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1423
int LGBM_BoosterGetNumFeature(BoosterHandle handle, int* out_len) {
wxchan's avatar
wxchan committed
1424
1425
1426
1427
1428
1429
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  *out_len = ref_booster->GetBoosting()->MaxFeatureIdx() + 1;
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1430
int LGBM_BoosterGetEval(BoosterHandle handle,
1431
1432
1433
                        int data_idx,
                        int* out_len,
                        double* out_results) {
1434
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1435
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1436
  auto boosting = ref_booster->GetBoosting();
wxchan's avatar
wxchan committed
1437
  auto result_buf = boosting->GetEvalAt(data_idx);
Guolin Ke's avatar
Guolin Ke committed
1438
  *out_len = static_cast<int>(result_buf.size());
1439
  for (size_t i = 0; i < result_buf.size(); ++i) {
Guolin Ke's avatar
Guolin Ke committed
1440
    (out_results)[i] = static_cast<double>(result_buf[i]);
1441
  }
1442
  API_END();
1443
1444
}

Guolin Ke's avatar
Guolin Ke committed
1445
int LGBM_BoosterGetNumPredict(BoosterHandle handle,
1446
1447
                              int data_idx,
                              int64_t* out_len) {
Guolin Ke's avatar
Guolin Ke committed
1448
1449
1450
1451
1452
1453
  API_BEGIN();
  auto boosting = reinterpret_cast<Booster*>(handle)->GetBoosting();
  *out_len = boosting->GetNumPredictAt(data_idx);
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1454
int LGBM_BoosterGetPredict(BoosterHandle handle,
1455
1456
1457
                           int data_idx,
                           int64_t* out_len,
                           double* out_result) {
1458
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1459
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1460
  ref_booster->GetPredictAt(data_idx, out_result, out_len);
1461
  API_END();
Guolin Ke's avatar
Guolin Ke committed
1462
1463
}

Guolin Ke's avatar
Guolin Ke committed
1464
int LGBM_BoosterPredictForFile(BoosterHandle handle,
1465
1466
1467
1468
                               const char* data_filename,
                               int data_has_header,
                               int predict_type,
                               int num_iteration,
1469
                               const char* parameter,
1470
                               const char* result_filename) {
1471
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1472
1473
  auto param = Config::Str2Map(parameter);
  Config config;
Guolin Ke's avatar
Guolin Ke committed
1474
1475
1476
1477
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
Guolin Ke's avatar
Guolin Ke committed
1478
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
cbecker's avatar
cbecker committed
1479
  ref_booster->Predict(num_iteration, predict_type, data_filename, data_has_header,
Guolin Ke's avatar
Guolin Ke committed
1480
                       config, result_filename);
1481
  API_END();
1482
1483
}

Guolin Ke's avatar
Guolin Ke committed
1484
int LGBM_BoosterCalcNumPredict(BoosterHandle handle,
1485
1486
1487
1488
                               int num_row,
                               int predict_type,
                               int num_iteration,
                               int64_t* out_len) {
Guolin Ke's avatar
Guolin Ke committed
1489
1490
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1491
1492
  *out_len = static_cast<int64_t>(num_row) * ref_booster->GetBoosting()->NumPredictOneRow(
    num_iteration, predict_type == C_API_PREDICT_LEAF_INDEX, predict_type == C_API_PREDICT_CONTRIB);
Guolin Ke's avatar
Guolin Ke committed
1493
1494
1495
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1496
int LGBM_BoosterPredictForCSR(BoosterHandle handle,
1497
1498
1499
1500
1501
1502
1503
                              const void* indptr,
                              int indptr_type,
                              const int32_t* indices,
                              const void* data,
                              int data_type,
                              int64_t nindptr,
                              int64_t nelem,
1504
                              int64_t num_col,
1505
1506
                              int predict_type,
                              int num_iteration,
1507
                              const char* parameter,
1508
1509
                              int64_t* out_len,
                              double* out_result) {
1510
  API_BEGIN();
1511
1512
1513
1514
1515
  if (num_col <= 0) {
    Log::Fatal("The number of columns should be greater than zero.");
  } else if (num_col >= INT32_MAX) {
    Log::Fatal("The number of columns should be smaller than INT32_MAX.");
  }
Guolin Ke's avatar
Guolin Ke committed
1516
1517
  auto param = Config::Str2Map(parameter);
  Config config;
Guolin Ke's avatar
Guolin Ke committed
1518
1519
1520
1521
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
Guolin Ke's avatar
Guolin Ke committed
1522
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1523
  auto get_row_fun = RowFunctionFromCSR(indptr, indptr_type, indices, data, data_type, nindptr, nelem);
Guolin Ke's avatar
Guolin Ke committed
1524
  int nrow = static_cast<int>(nindptr - 1);
1525
  ref_booster->Predict(num_iteration, predict_type, nrow, static_cast<int>(num_col), get_row_fun,
Guolin Ke's avatar
Guolin Ke committed
1526
                       config, out_result, out_len);
1527
  API_END();
Guolin Ke's avatar
Guolin Ke committed
1528
}
1529

1530
int LGBM_BoosterPredictForCSRSingleRow(BoosterHandle handle,
1531
1532
1533
1534
1535
1536
1537
                                       const void* indptr,
                                       int indptr_type,
                                       const int32_t* indices,
                                       const void* data,
                                       int data_type,
                                       int64_t nindptr,
                                       int64_t nelem,
1538
                                       int64_t num_col,
1539
1540
1541
1542
1543
                                       int predict_type,
                                       int num_iteration,
                                       const char* parameter,
                                       int64_t* out_len,
                                       double* out_result) {
1544
  API_BEGIN();
1545
1546
1547
1548
1549
  if (num_col <= 0) {
    Log::Fatal("The number of columns should be greater than zero.");
  } else if (num_col >= INT32_MAX) {
    Log::Fatal("The number of columns should be smaller than INT32_MAX.");
  }
1550
1551
1552
1553
1554
1555
1556
1557
  auto param = Config::Str2Map(parameter);
  Config config;
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  auto get_row_fun = RowFunctionFromCSR(indptr, indptr_type, indices, data, data_type, nindptr, nelem);
1558
  ref_booster->PredictSingleRow(num_iteration, predict_type, static_cast<int32_t>(num_col), get_row_fun, config, out_result, out_len);
1559
1560
1561
1562
  API_END();
}


Guolin Ke's avatar
Guolin Ke committed
1563
int LGBM_BoosterPredictForCSC(BoosterHandle handle,
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
                              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,
1574
                              const char* parameter,
1575
1576
                              int64_t* out_len,
                              double* out_result) {
Guolin Ke's avatar
Guolin Ke committed
1577
1578
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
Guolin Ke's avatar
Guolin Ke committed
1579
1580
  auto param = Config::Str2Map(parameter);
  Config config;
Guolin Ke's avatar
Guolin Ke committed
1581
1582
1583
1584
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
1585
  int num_threads = OMP_NUM_THREADS();
Guolin Ke's avatar
Guolin Ke committed
1586
  int ncol = static_cast<int>(ncol_ptr - 1);
Guolin Ke's avatar
Guolin Ke committed
1587
1588
1589
1590
1591
  std::vector<std::vector<CSC_RowIterator>> iterators(num_threads, std::vector<CSC_RowIterator>());
  for (int i = 0; i < num_threads; ++i) {
    for (int j = 0; j < ncol; ++j) {
      iterators[i].emplace_back(col_ptr, col_ptr_type, indices, data, data_type, ncol_ptr, nelem, j);
    }
Guolin Ke's avatar
Guolin Ke committed
1592
1593
  }
  std::function<std::vector<std::pair<int, double>>(int row_idx)> get_row_fun =
Guolin Ke's avatar
Guolin Ke committed
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
      [&iterators, ncol](int i) {
        std::vector<std::pair<int, double>> one_row;
        one_row.reserve(ncol);
        const int tid = omp_get_thread_num();
        for (int j = 0; j < ncol; ++j) {
          auto val = iterators[tid][j].Get(i);
          if (std::fabs(val) > kZeroThreshold || std::isnan(val)) {
            one_row.emplace_back(j, val);
          }
        }
        return one_row;
      };
1606
  ref_booster->Predict(num_iteration, predict_type, static_cast<int>(num_row), ncol, get_row_fun, config,
cbecker's avatar
cbecker committed
1607
                       out_result, out_len);
Guolin Ke's avatar
Guolin Ke committed
1608
1609
1610
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1611
int LGBM_BoosterPredictForMat(BoosterHandle handle,
1612
1613
1614
1615
1616
1617
1618
                              const void* data,
                              int data_type,
                              int32_t nrow,
                              int32_t ncol,
                              int is_row_major,
                              int predict_type,
                              int num_iteration,
1619
                              const char* parameter,
1620
1621
                              int64_t* out_len,
                              double* out_result) {
1622
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1623
1624
  auto param = Config::Str2Map(parameter);
  Config config;
Guolin Ke's avatar
Guolin Ke committed
1625
1626
1627
1628
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
Guolin Ke's avatar
Guolin Ke committed
1629
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1630
  auto get_row_fun = RowPairFunctionFromDenseMatric(data, nrow, ncol, data_type, is_row_major);
1631
  ref_booster->Predict(num_iteration, predict_type, nrow, ncol, get_row_fun,
Guolin Ke's avatar
Guolin Ke committed
1632
                       config, out_result, out_len);
1633
  API_END();
Guolin Ke's avatar
Guolin Ke committed
1634
}
1635

1636
int LGBM_BoosterPredictForMatSingleRow(BoosterHandle handle,
1637
1638
1639
1640
1641
1642
1643
1644
1645
                                       const void* data,
                                       int data_type,
                                       int32_t ncol,
                                       int is_row_major,
                                       int predict_type,
                                       int num_iteration,
                                       const char* parameter,
                                       int64_t* out_len,
                                       double* out_result) {
1646
1647
1648
1649
1650
1651
1652
1653
1654
  API_BEGIN();
  auto param = Config::Str2Map(parameter);
  Config config;
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  auto get_row_fun = RowPairFunctionFromDenseMatric(data, 1, ncol, data_type, is_row_major);
1655
  ref_booster->PredictSingleRow(num_iteration, predict_type, ncol, get_row_fun, config, out_result, out_len);
1656
1657
1658
1659
  API_END();
}


1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
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) {
  API_BEGIN();
  auto param = Config::Str2Map(parameter);
  Config config;
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  auto get_row_fun = RowPairFunctionFromDenseRows(data, ncol, data_type);
1679
  ref_booster->Predict(num_iteration, predict_type, nrow, ncol, get_row_fun, config, out_result, out_len);
1680
1681
1682
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1683
int LGBM_BoosterSaveModel(BoosterHandle handle,
1684
                          int start_iteration,
1685
1686
                          int num_iteration,
                          const char* filename) {
1687
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1688
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1689
  ref_booster->SaveModelToFile(start_iteration, num_iteration, filename);
wxchan's avatar
wxchan committed
1690
1691
1692
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1693
int LGBM_BoosterSaveModelToString(BoosterHandle handle,
1694
                                  int start_iteration,
1695
                                  int num_iteration,
1696
                                  int64_t buffer_len,
1697
                                  int64_t* out_len,
1698
                                  char* out_str) {
1699
1700
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1701
  std::string model = ref_booster->SaveModelToString(start_iteration, num_iteration);
1702
  *out_len = static_cast<int64_t>(model.size()) + 1;
1703
  if (*out_len <= buffer_len) {
Guolin Ke's avatar
Guolin Ke committed
1704
    std::memcpy(out_str, model.c_str(), *out_len);
1705
1706
1707
1708
  }
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1709
int LGBM_BoosterDumpModel(BoosterHandle handle,
1710
                          int start_iteration,
1711
                          int num_iteration,
1712
1713
                          int64_t buffer_len,
                          int64_t* out_len,
1714
                          char* out_str) {
wxchan's avatar
wxchan committed
1715
1716
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
1717
  std::string model = ref_booster->DumpModel(start_iteration, num_iteration);
1718
  *out_len = static_cast<int64_t>(model.size()) + 1;
wxchan's avatar
wxchan committed
1719
  if (*out_len <= buffer_len) {
Guolin Ke's avatar
Guolin Ke committed
1720
    std::memcpy(out_str, model.c_str(), *out_len);
wxchan's avatar
wxchan committed
1721
  }
1722
  API_END();
Guolin Ke's avatar
Guolin Ke committed
1723
}
1724

Guolin Ke's avatar
Guolin Ke committed
1725
int LGBM_BoosterGetLeafValue(BoosterHandle handle,
1726
1727
1728
                             int tree_idx,
                             int leaf_idx,
                             double* out_val) {
Guolin Ke's avatar
Guolin Ke committed
1729
1730
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
Guolin Ke's avatar
Guolin Ke committed
1731
  *out_val = static_cast<double>(ref_booster->GetLeafValue(tree_idx, leaf_idx));
Guolin Ke's avatar
Guolin Ke committed
1732
1733
1734
  API_END();
}

Guolin Ke's avatar
Guolin Ke committed
1735
int LGBM_BoosterSetLeafValue(BoosterHandle handle,
1736
1737
1738
                             int tree_idx,
                             int leaf_idx,
                             double val) {
Guolin Ke's avatar
Guolin Ke committed
1739
1740
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
Guolin Ke's avatar
Guolin Ke committed
1741
  ref_booster->SetLeafValue(tree_idx, leaf_idx, val);
Guolin Ke's avatar
Guolin Ke committed
1742
1743
1744
  API_END();
}

1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
int LGBM_BoosterFeatureImportance(BoosterHandle handle,
                                  int num_iteration,
                                  int importance_type,
                                  double* out_results) {
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  std::vector<double> feature_importances = ref_booster->FeatureImportance(num_iteration, importance_type);
  for (size_t i = 0; i < feature_importances.size(); ++i) {
    (out_results)[i] = feature_importances[i];
  }
  API_END();
}

1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
int LGBM_BoosterGetUpperBoundValue(BoosterHandle handle,
                                   double* out_results) {
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  double max_value = ref_booster->UpperBoundValue();
  *out_results = max_value;
  API_END();
}

int LGBM_BoosterGetLowerBoundValue(BoosterHandle handle,
                                   double* out_results) {
  API_BEGIN();
  Booster* ref_booster = reinterpret_cast<Booster*>(handle);
  double min_value = ref_booster->LowerBoundValue();
  *out_results = min_value;
  API_END();
}

1776
1777
1778
1779
1780
int LGBM_NetworkInit(const char* machines,
                     int local_listen_port,
                     int listen_time_out,
                     int num_machines) {
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1781
  Config config;
1782
  config.machines = RemoveQuotationSymbol(std::string(machines));
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
  config.local_listen_port = local_listen_port;
  config.num_machines = num_machines;
  config.time_out = listen_time_out;
  if (num_machines > 1) {
    Network::Init(config);
  }
  API_END();
}

int LGBM_NetworkFree() {
  API_BEGIN();
  Network::Dispose();
  API_END();
}

1798
1799
1800
int LGBM_NetworkInitWithFunctions(int num_machines, int rank,
                                  void* reduce_scatter_ext_fun,
                                  void* allgather_ext_fun) {
ww's avatar
ww committed
1801
  API_BEGIN();
Guolin Ke's avatar
Guolin Ke committed
1802
  if (num_machines > 1) {
1803
    Network::Init(num_machines, rank, (ReduceScatterFunction)reduce_scatter_ext_fun, (AllgatherFunction)allgather_ext_fun);
ww's avatar
ww committed
1804
1805
1806
  }
  API_END();
}
Guolin Ke's avatar
Guolin Ke committed
1807

Guolin Ke's avatar
Guolin Ke committed
1808
// ---- start of some help functions
1809
1810
1811

std::function<std::vector<double>(int row_idx)>
RowFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_type, int is_row_major) {
Guolin Ke's avatar
Guolin Ke committed
1812
  if (data_type == C_API_DTYPE_FLOAT32) {
1813
1814
    const float* data_ptr = reinterpret_cast<const float*>(data);
    if (is_row_major) {
1815
      return [=] (int row_idx) {
Guolin Ke's avatar
Guolin Ke committed
1816
        std::vector<double> ret(num_col);
1817
        auto tmp_ptr = data_ptr + static_cast<size_t>(num_col) * row_idx;
1818
        for (int i = 0; i < num_col; ++i) {
Guolin Ke's avatar
Guolin Ke committed
1819
          ret[i] = static_cast<double>(*(tmp_ptr + i));
1820
1821
1822
1823
        }
        return ret;
      };
    } else {
1824
      return [=] (int row_idx) {
Guolin Ke's avatar
Guolin Ke committed
1825
        std::vector<double> ret(num_col);
1826
        for (int i = 0; i < num_col; ++i) {
1827
          ret[i] = static_cast<double>(*(data_ptr + static_cast<size_t>(num_row) * i + row_idx));
1828
1829
1830
1831
        }
        return ret;
      };
    }
Guolin Ke's avatar
Guolin Ke committed
1832
  } else if (data_type == C_API_DTYPE_FLOAT64) {
1833
1834
    const double* data_ptr = reinterpret_cast<const double*>(data);
    if (is_row_major) {
1835
      return [=] (int row_idx) {
Guolin Ke's avatar
Guolin Ke committed
1836
        std::vector<double> ret(num_col);
1837
        auto tmp_ptr = data_ptr + static_cast<size_t>(num_col) * row_idx;
1838
        for (int i = 0; i < num_col; ++i) {
Guolin Ke's avatar
Guolin Ke committed
1839
          ret[i] = static_cast<double>(*(tmp_ptr + i));
1840
1841
1842
1843
        }
        return ret;
      };
    } else {
1844
      return [=] (int row_idx) {
Guolin Ke's avatar
Guolin Ke committed
1845
        std::vector<double> ret(num_col);
1846
        for (int i = 0; i < num_col; ++i) {
1847
          ret[i] = static_cast<double>(*(data_ptr + static_cast<size_t>(num_row) * i + row_idx));
1848
1849
1850
1851
1852
        }
        return ret;
      };
    }
  }
1853
  Log::Fatal("Unknown data type in RowFunctionFromDenseMatric");
1854
  return nullptr;
1855
1856
1857
1858
}

std::function<std::vector<std::pair<int, double>>(int row_idx)>
RowPairFunctionFromDenseMatric(const void* data, int num_row, int num_col, int data_type, int is_row_major) {
Guolin Ke's avatar
Guolin Ke committed
1859
1860
  auto inner_function = RowFunctionFromDenseMatric(data, num_row, num_col, data_type, is_row_major);
  if (inner_function != nullptr) {
1861
    return [inner_function] (int row_idx) {
Guolin Ke's avatar
Guolin Ke committed
1862
1863
      auto raw_values = inner_function(row_idx);
      std::vector<std::pair<int, double>> ret;
Guolin Ke's avatar
Guolin Ke committed
1864
      ret.reserve(raw_values.size());
Guolin Ke's avatar
Guolin Ke committed
1865
      for (int i = 0; i < static_cast<int>(raw_values.size()); ++i) {
Guolin Ke's avatar
Guolin Ke committed
1866
        if (std::fabs(raw_values[i]) > kZeroThreshold || std::isnan(raw_values[i])) {
Guolin Ke's avatar
Guolin Ke committed
1867
          ret.emplace_back(i, raw_values[i]);
1868
        }
Guolin Ke's avatar
Guolin Ke committed
1869
1870
1871
      }
      return ret;
    };
1872
  }
Guolin Ke's avatar
Guolin Ke committed
1873
  return nullptr;
1874
1875
}

1876
1877
1878
1879
1880
1881
1882
// data is array of pointers to individual rows
std::function<std::vector<std::pair<int, double>>(int row_idx)>
RowPairFunctionFromDenseRows(const void** data, int num_col, int data_type) {
  return [=](int row_idx) {
    auto inner_function = RowFunctionFromDenseMatric(data[row_idx], 1, num_col, data_type, /* is_row_major */ true);
    auto raw_values = inner_function(0);
    std::vector<std::pair<int, double>> ret;
Guolin Ke's avatar
Guolin Ke committed
1883
    ret.reserve(raw_values.size());
1884
1885
1886
1887
1888
1889
1890
1891
1892
    for (int i = 0; i < static_cast<int>(raw_values.size()); ++i) {
      if (std::fabs(raw_values[i]) > kZeroThreshold || std::isnan(raw_values[i])) {
        ret.emplace_back(i, raw_values[i]);
      }
    }
    return ret;
  };
}

1893
std::function<std::vector<std::pair<int, double>>(int idx)>
1894
RowFunctionFromCSR(const void* indptr, int indptr_type, const int32_t* indices, const void* data, int data_type, int64_t , int64_t ) {
Guolin Ke's avatar
Guolin Ke committed
1895
  if (data_type == C_API_DTYPE_FLOAT32) {
1896
    const float* data_ptr = reinterpret_cast<const float*>(data);
Guolin Ke's avatar
Guolin Ke committed
1897
    if (indptr_type == C_API_DTYPE_INT32) {
1898
      const int32_t* ptr_indptr = reinterpret_cast<const int32_t*>(indptr);
1899
      return [=] (int idx) {
1900
1901
1902
        std::vector<std::pair<int, double>> ret;
        int64_t start = ptr_indptr[idx];
        int64_t end = ptr_indptr[idx + 1];
1903
1904
1905
        if (end - start > 0)  {
          ret.reserve(end - start);
        }
Guolin Ke's avatar
Guolin Ke committed
1906
        for (int64_t i = start; i < end; ++i) {
Guolin Ke's avatar
Guolin Ke committed
1907
          ret.emplace_back(indices[i], data_ptr[i]);
1908
1909
1910
        }
        return ret;
      };
Guolin Ke's avatar
Guolin Ke committed
1911
    } else if (indptr_type == C_API_DTYPE_INT64) {
1912
      const int64_t* ptr_indptr = reinterpret_cast<const int64_t*>(indptr);
1913
      return [=] (int idx) {
1914
1915
1916
        std::vector<std::pair<int, double>> ret;
        int64_t start = ptr_indptr[idx];
        int64_t end = ptr_indptr[idx + 1];
1917
1918
1919
        if (end - start > 0)  {
          ret.reserve(end - start);
        }
Guolin Ke's avatar
Guolin Ke committed
1920
        for (int64_t i = start; i < end; ++i) {
Guolin Ke's avatar
Guolin Ke committed
1921
          ret.emplace_back(indices[i], data_ptr[i]);
1922
1923
1924
1925
        }
        return ret;
      };
    }
Guolin Ke's avatar
Guolin Ke committed
1926
  } else if (data_type == C_API_DTYPE_FLOAT64) {
1927
    const double* data_ptr = reinterpret_cast<const double*>(data);
Guolin Ke's avatar
Guolin Ke committed
1928
    if (indptr_type == C_API_DTYPE_INT32) {
1929
      const int32_t* ptr_indptr = reinterpret_cast<const int32_t*>(indptr);
1930
      return [=] (int idx) {
1931
1932
1933
        std::vector<std::pair<int, double>> ret;
        int64_t start = ptr_indptr[idx];
        int64_t end = ptr_indptr[idx + 1];
1934
1935
1936
        if (end - start > 0)  {
          ret.reserve(end - start);
        }
Guolin Ke's avatar
Guolin Ke committed
1937
        for (int64_t i = start; i < end; ++i) {
Guolin Ke's avatar
Guolin Ke committed
1938
          ret.emplace_back(indices[i], data_ptr[i]);
1939
1940
1941
        }
        return ret;
      };
Guolin Ke's avatar
Guolin Ke committed
1942
    } else if (indptr_type == C_API_DTYPE_INT64) {
1943
      const int64_t* ptr_indptr = reinterpret_cast<const int64_t*>(indptr);
1944
      return [=] (int idx) {
1945
1946
1947
        std::vector<std::pair<int, double>> ret;
        int64_t start = ptr_indptr[idx];
        int64_t end = ptr_indptr[idx + 1];
1948
1949
1950
        if (end - start > 0)  {
          ret.reserve(end - start);
        }
Guolin Ke's avatar
Guolin Ke committed
1951
        for (int64_t i = start; i < end; ++i) {
Guolin Ke's avatar
Guolin Ke committed
1952
          ret.emplace_back(indices[i], data_ptr[i]);
1953
1954
1955
        }
        return ret;
      };
Guolin Ke's avatar
Guolin Ke committed
1956
1957
    }
  }
1958
  Log::Fatal("Unknown data type in RowFunctionFromCSR");
1959
  return nullptr;
1960
1961
}

Guolin Ke's avatar
Guolin Ke committed
1962
std::function<std::pair<int, double>(int idx)>
1963
IterateFunctionFromCSC(const void* col_ptr, int col_ptr_type, const int32_t* indices, const void* data, int data_type, int64_t ncol_ptr, int64_t , int col_idx) {
Guolin Ke's avatar
Guolin Ke committed
1964
  CHECK(col_idx < ncol_ptr && col_idx >= 0);
Guolin Ke's avatar
Guolin Ke committed
1965
  if (data_type == C_API_DTYPE_FLOAT32) {
1966
    const float* data_ptr = reinterpret_cast<const float*>(data);
Guolin Ke's avatar
Guolin Ke committed
1967
    if (col_ptr_type == C_API_DTYPE_INT32) {
1968
      const int32_t* ptr_col_ptr = reinterpret_cast<const int32_t*>(col_ptr);
Guolin Ke's avatar
Guolin Ke committed
1969
1970
      int64_t start = ptr_col_ptr[col_idx];
      int64_t end = ptr_col_ptr[col_idx + 1];
1971
1972
      return [=] (int offset) {
        int64_t i = static_cast<int64_t>(start + offset);
Guolin Ke's avatar
Guolin Ke committed
1973
1974
        if (i >= end) {
          return std::make_pair(-1, 0.0);
1975
        }
Guolin Ke's avatar
Guolin Ke committed
1976
1977
1978
        int idx = static_cast<int>(indices[i]);
        double val = static_cast<double>(data_ptr[i]);
        return std::make_pair(idx, val);
1979
      };
Guolin Ke's avatar
Guolin Ke committed
1980
    } else if (col_ptr_type == C_API_DTYPE_INT64) {
1981
      const int64_t* ptr_col_ptr = reinterpret_cast<const int64_t*>(col_ptr);
Guolin Ke's avatar
Guolin Ke committed
1982
1983
      int64_t start = ptr_col_ptr[col_idx];
      int64_t end = ptr_col_ptr[col_idx + 1];
1984
1985
      return [=] (int offset) {
        int64_t i = static_cast<int64_t>(start + offset);
Guolin Ke's avatar
Guolin Ke committed
1986
1987
        if (i >= end) {
          return std::make_pair(-1, 0.0);
1988
        }
Guolin Ke's avatar
Guolin Ke committed
1989
1990
1991
        int idx = static_cast<int>(indices[i]);
        double val = static_cast<double>(data_ptr[i]);
        return std::make_pair(idx, val);
1992
      };
Guolin Ke's avatar
Guolin Ke committed
1993
    }
Guolin Ke's avatar
Guolin Ke committed
1994
  } else if (data_type == C_API_DTYPE_FLOAT64) {
1995
    const double* data_ptr = reinterpret_cast<const double*>(data);
Guolin Ke's avatar
Guolin Ke committed
1996
    if (col_ptr_type == C_API_DTYPE_INT32) {
1997
      const int32_t* ptr_col_ptr = reinterpret_cast<const int32_t*>(col_ptr);
Guolin Ke's avatar
Guolin Ke committed
1998
1999
      int64_t start = ptr_col_ptr[col_idx];
      int64_t end = ptr_col_ptr[col_idx + 1];
2000
2001
      return [=] (int offset) {
        int64_t i = static_cast<int64_t>(start + offset);
Guolin Ke's avatar
Guolin Ke committed
2002
2003
        if (i >= end) {
          return std::make_pair(-1, 0.0);
2004
        }
Guolin Ke's avatar
Guolin Ke committed
2005
2006
2007
        int idx = static_cast<int>(indices[i]);
        double val = static_cast<double>(data_ptr[i]);
        return std::make_pair(idx, val);
2008
      };
Guolin Ke's avatar
Guolin Ke committed
2009
    } else if (col_ptr_type == C_API_DTYPE_INT64) {
2010
      const int64_t* ptr_col_ptr = reinterpret_cast<const int64_t*>(col_ptr);
Guolin Ke's avatar
Guolin Ke committed
2011
2012
      int64_t start = ptr_col_ptr[col_idx];
      int64_t end = ptr_col_ptr[col_idx + 1];
2013
2014
      return [=] (int offset) {
        int64_t i = static_cast<int64_t>(start + offset);
Guolin Ke's avatar
Guolin Ke committed
2015
2016
        if (i >= end) {
          return std::make_pair(-1, 0.0);
2017
        }
Guolin Ke's avatar
Guolin Ke committed
2018
2019
2020
        int idx = static_cast<int>(indices[i]);
        double val = static_cast<double>(data_ptr[i]);
        return std::make_pair(idx, val);
2021
      };
Guolin Ke's avatar
Guolin Ke committed
2022
2023
    }
  }
2024
  Log::Fatal("Unknown data type in CSC matrix");
2025
  return nullptr;
2026
2027
}

Guolin Ke's avatar
Guolin Ke committed
2028
CSC_RowIterator::CSC_RowIterator(const void* col_ptr, int col_ptr_type, const int32_t* indices,
2029
                                 const void* data, int data_type, int64_t ncol_ptr, int64_t nelem, int col_idx) {
Guolin Ke's avatar
Guolin Ke committed
2030
2031
2032
2033
2034
2035
2036
2037
2038
  iter_fun_ = IterateFunctionFromCSC(col_ptr, col_ptr_type, indices, data, data_type, ncol_ptr, nelem, col_idx);
}

double CSC_RowIterator::Get(int idx) {
  while (idx > cur_idx_ && !is_end_) {
    auto ret = iter_fun_(nonzero_idx_);
    if (ret.first < 0) {
      is_end_ = true;
      break;
2039
    }
Guolin Ke's avatar
Guolin Ke committed
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
    cur_idx_ = ret.first;
    cur_val_ = ret.second;
    ++nonzero_idx_;
  }
  if (idx == cur_idx_) {
    return cur_val_;
  } else {
    return 0.0f;
  }
}

std::pair<int, double> CSC_RowIterator::NextNonZero() {
  if (!is_end_) {
    auto ret = iter_fun_(nonzero_idx_);
    ++nonzero_idx_;
    if (ret.first < 0) {
      is_end_ = true;
2057
    }
Guolin Ke's avatar
Guolin Ke committed
2058
2059
2060
    return ret;
  } else {
    return std::make_pair(-1, 0.0);
2061
  }
Guolin Ke's avatar
Guolin Ke committed
2062
}