"examples/vscode:/vscode.git/clone" did not exist on "3e285d7d152da751a86d76897e6eecaacb170869"
metadata.cpp 14 KB
Newer Older
Guolin Ke's avatar
Guolin Ke committed
1
2
3
4
5
6
7
8
9
10
#include <LightGBM/dataset.h>

#include <LightGBM/utils/common.h>

#include <vector>
#include <string>

namespace LightGBM {

Metadata::Metadata()
Guolin Ke's avatar
Guolin Ke committed
11
  :label_(nullptr), weights_(nullptr), 
Guolin Ke's avatar
Guolin Ke committed
12
  query_boundaries_(nullptr),
Guolin Ke's avatar
Guolin Ke committed
13
  query_weights_(nullptr), init_score_(nullptr), queries_(nullptr){
Guolin Ke's avatar
Guolin Ke committed
14
15
16

}

17
void Metadata::Init(const char * data_filename, const char* init_score_filename, const int num_class) {
Guolin Ke's avatar
Guolin Ke committed
18
19
  data_filename_ = data_filename;
  init_score_filename_ = init_score_filename;
20
  num_class_ = num_class;
Guolin Ke's avatar
Guolin Ke committed
21
22
23
24
25
26
27
  // for lambdarank, it needs query data for partition data in parallel learning
  LoadQueryBoundaries();
  LoadWeights();
  LoadQueryWeights();
  LoadInitialScore();
}

28
void Metadata::Init(const char* init_score_filename, const int num_class) {
Guolin Ke's avatar
Guolin Ke committed
29
  init_score_filename_ = init_score_filename;
30
  num_class_ = num_class;
Guolin Ke's avatar
Guolin Ke committed
31
32
33
34
35
36
37
38
39
40
  LoadInitialScore();
}


Metadata::~Metadata() {
  if (label_ != nullptr) { delete[] label_; }
  if (weights_ != nullptr) { delete[] weights_; }
  if (query_boundaries_ != nullptr) { delete[] query_boundaries_; }
  if (query_weights_ != nullptr) { delete[] query_weights_; }
  if (init_score_ != nullptr) { delete[] init_score_; }
Guolin Ke's avatar
Guolin Ke committed
41
  if (queries_ != nullptr) { delete[] queries_; }
Guolin Ke's avatar
Guolin Ke committed
42
43
44
}


45
void Metadata::Init(data_size_t num_data, int num_class, int weight_idx, int query_idx) {
Guolin Ke's avatar
Guolin Ke committed
46
  num_data_ = num_data;
47
  num_class_ = num_class;
Guolin Ke's avatar
Guolin Ke committed
48
  label_ = new float[num_data_];
Guolin Ke's avatar
Guolin Ke committed
49
50
  if (weight_idx >= 0) {
    if (weights_ != nullptr) {
51
52
      Log::Info("Using weights in data file, ignoring the additional weights file");
      delete[] weights_;
Guolin Ke's avatar
Guolin Ke committed
53
54
55
56
57
58
59
    }
    weights_ = new float[num_data_];
    num_weights_ = num_data_;
    memset(weights_, 0, sizeof(float) * num_data_);
  }
  if (query_idx >= 0) {
    if (query_boundaries_ != nullptr) {
60
      Log::Info("Using query id in data file, ignoring the additional query file");
Guolin Ke's avatar
Guolin Ke committed
61
62
63
64
65
66
      delete[] query_boundaries_;
    }
    if (query_weights_ != nullptr) { delete[] query_weights_; }
    queries_ = new data_size_t[num_data_];
    memset(queries_, 0, sizeof(data_size_t) * num_data_);
  }
Guolin Ke's avatar
Guolin Ke committed
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
}

void Metadata::PartitionLabel(const std::vector<data_size_t>& used_indices) {
  if (used_indices.size() <= 0) {
    return;
  }
  float* old_label = label_;
  num_data_ = static_cast<data_size_t>(used_indices.size());
  label_ = new float[num_data_];
  for (data_size_t i = 0; i < num_data_; ++i) {
    label_[i] = old_label[used_indices[i]];
  }
  delete[] old_label;
}

void Metadata::CheckOrPartition(data_size_t num_all_data, const std::vector<data_size_t>& used_data_indices) {
  if (used_data_indices.size() == 0) {
Guolin Ke's avatar
Guolin Ke committed
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
    if (queries_ != nullptr) {
      // need convert query_id to boundaries
      std::vector<data_size_t> tmp_buffer;
      data_size_t last_qid = -1;
      data_size_t cur_cnt = 0;
      for (data_size_t i = 0; i < num_data_; ++i) {
        if (last_qid != queries_[i]) {
          if (cur_cnt > 0) {
            tmp_buffer.push_back(cur_cnt);
          }
          cur_cnt = 0;
          last_qid = queries_[i];
        }
        ++cur_cnt;
      }
      tmp_buffer.push_back(cur_cnt);
      query_boundaries_ = new data_size_t[tmp_buffer.size() + 1];
      num_queries_ = static_cast<data_size_t>(tmp_buffer.size());
      query_boundaries_[0] = 0;
      for (size_t i = 0; i < tmp_buffer.size(); ++i) {
        query_boundaries_[i + 1] = query_boundaries_[i] + tmp_buffer[i];
      }
      LoadQueryWeights();
      delete[] queries_;
      queries_ = nullptr;
    }
Guolin Ke's avatar
Guolin Ke committed
110
111
    // check weights
    if (weights_ != nullptr && num_weights_ != num_data_) {
112
      Log::Fatal("Weights size doesn't match data size");
Guolin Ke's avatar
Guolin Ke committed
113
114
115
116
117
118
119
      delete[] weights_;
      num_weights_ = 0;
      weights_ = nullptr;
    }

    // check query boundries
    if (query_boundaries_ != nullptr && query_boundaries_[num_queries_] != num_data_) {
120
      Log::Fatal("Query size doesn't match data size");
Guolin Ke's avatar
Guolin Ke committed
121
122
123
124
125
126
127
128
      delete[] query_boundaries_;
      num_queries_ = 0;
      query_boundaries_ = nullptr;
    }

    // contain initial score file
    if (init_score_ != nullptr && num_init_score_ != num_data_) {
      delete[] init_score_;
129
      Log::Fatal("Initial score size doesn't match data size");
130
      init_score_ = nullptr;
Guolin Ke's avatar
Guolin Ke committed
131
132
133
134
135
136
      num_init_score_ = 0;
    }
  } else {
    data_size_t num_used_data = static_cast<data_size_t>(used_data_indices.size());
    // check weights
    if (weights_ != nullptr && num_weights_ != num_all_data) {
137
      Log::Fatal("Weights size doesn't match data size");
Guolin Ke's avatar
Guolin Ke committed
138
139
140
141
142
143
      delete[] weights_;
      num_weights_ = 0;
      weights_ = nullptr;
    }
    // check query boundries
    if (query_boundaries_ != nullptr && query_boundaries_[num_queries_] != num_all_data) {
144
      Log::Fatal("Query size doesn't match data size");
Guolin Ke's avatar
Guolin Ke committed
145
146
147
148
149
150
151
      delete[] query_boundaries_;
      num_queries_ = 0;
      query_boundaries_ = nullptr;
    }

    // contain initial score file
    if (init_score_ != nullptr && num_init_score_ != num_all_data) {
152
      Log::Fatal("Initial score size doesn't match data size");
Guolin Ke's avatar
Guolin Ke committed
153
154
      delete[] init_score_;
      num_init_score_ = 0;
155
      init_score_ = nullptr;
Guolin Ke's avatar
Guolin Ke committed
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
    }

    // get local weights
    if (weights_ != nullptr) {
      float* old_weights = weights_;
      num_weights_ = num_data_;
      weights_ = new float[num_data_];
      for (size_t i = 0; i < used_data_indices.size(); ++i) {
        weights_[i] = old_weights[used_data_indices[i]];
      }
      delete[] old_weights;
    }

    // get local query boundaries
    if (query_boundaries_ != nullptr) {
      std::vector<data_size_t> used_query;
      data_size_t data_idx = 0;
      for (data_size_t qid = 0; qid < num_queries_ && data_idx < num_used_data; ++qid) {
        data_size_t start = query_boundaries_[qid];
        data_size_t end = query_boundaries_[qid + 1];
        data_size_t len = end - start;
        if (used_data_indices[data_idx] > start) {
          continue;
        } else if (used_data_indices[data_idx] == start) {
          if (num_used_data >= data_idx + len && used_data_indices[data_idx + len - 1] == end - 1) {
            used_query.push_back(qid);
            data_idx += len;
          } else {
Guolin Ke's avatar
Guolin Ke committed
184
            Log::Fatal("Data partition error, data didn't match queries");
Guolin Ke's avatar
Guolin Ke committed
185
186
          }
        } else {
Guolin Ke's avatar
Guolin Ke committed
187
          Log::Fatal("Data partition error, data didn't match queries");
Guolin Ke's avatar
Guolin Ke committed
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
        }
      }
      data_size_t * old_query_boundaries = query_boundaries_;
      query_boundaries_ = new data_size_t[used_query.size() + 1];
      num_queries_ = static_cast<data_size_t>(used_query.size());
      query_boundaries_[0] = 0;
      for (data_size_t i = 0; i < num_queries_; ++i) {
        data_size_t qid = used_query[i];
        data_size_t len = old_query_boundaries[qid + 1] - old_query_boundaries[qid];
        query_boundaries_[i + 1] = query_boundaries_[i] + len;
      }
      delete[] old_query_boundaries;
    }

    // get local initial scores
    if (init_score_ != nullptr) {
Guolin Ke's avatar
Guolin Ke committed
204
      float* old_scores = init_score_;
Guolin Ke's avatar
Guolin Ke committed
205
      num_init_score_ = num_data_;
206
207
208
209
      init_score_ = new float[num_init_score_ * num_class_];
      for (int k = 0; k < num_class_; ++k){
        for (size_t i = 0; i < used_data_indices.size(); ++i) {
          init_score_[k * num_data_ + i] = old_scores[k * num_all_data + used_data_indices[i]];
210
        }
Guolin Ke's avatar
Guolin Ke committed
211
212
213
214
215
216
217
218
219
220
      }
      delete[] old_scores;
    }

    // re-load query weight
    LoadQueryWeights();
  }
}


Guolin Ke's avatar
Guolin Ke committed
221
void Metadata::SetInitScore(const float* init_score, data_size_t len) {
222
  if (len != num_data_ * num_class_) {
223
    Log::Fatal("Initial score size doesn't match data size");
Guolin Ke's avatar
Guolin Ke committed
224
  }
Guolin Ke's avatar
Guolin Ke committed
225
226
  if (init_score_ != nullptr) { delete[] init_score_; }
  num_init_score_ = num_data_;
227
228
  init_score_ = new float[len];
  for (data_size_t i = 0; i < len; ++i) {
Guolin Ke's avatar
Guolin Ke committed
229
230
    init_score_[i] = init_score[i];
  }
Guolin Ke's avatar
Guolin Ke committed
231
232
}

Guolin Ke's avatar
Guolin Ke committed
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
void Metadata::SetLabel(const float* label, data_size_t len) {
  if (num_data_ != len) {
    Log::Fatal("len of label is not same with #data");
  }
  if (label_ != nullptr) { delete[] label_; }
  label_ = new float[num_data_];
  for (data_size_t i = 0; i < num_data_; ++i) {
    label_[i] = label[i];
  }
}

void Metadata::SetWeights(const float* weights, data_size_t len) {
  if (num_data_ != len) {
    Log::Fatal("len of weights is not same with #data");
  }
  if (weights_ != nullptr) { delete[] weights_; }
  num_weights_ = num_data_;
  weights_ = new float[num_weights_];
  for (data_size_t i = 0; i < num_weights_; ++i) {
    weights_[i] = weights[i];
  }
  LoadQueryWeights();
}

void Metadata::SetQueryBoundaries(const data_size_t* query_boundaries, data_size_t len) {
  data_size_t sum = 0;
  for (data_size_t i = 0; i < len; ++i) {
    sum += query_boundaries[i];
  }
  if (num_data_ != sum) {
    Log::Fatal("sum of query counts is not same with #data");
  }
  if (query_boundaries_ != nullptr) { delete[] query_boundaries_; }
  num_queries_ = len;
  query_boundaries_ = new data_size_t[num_queries_];
  for (data_size_t i = 0; i < num_queries_; ++i) {
    query_boundaries_[i] = query_boundaries[i];
  }
  LoadQueryWeights();
}


Guolin Ke's avatar
Guolin Ke committed
275
276
277
278
279
void Metadata::LoadWeights() {
  num_weights_ = 0;
  std::string weight_filename(data_filename_);
  // default weight file name
  weight_filename.append(".weight");
Guolin Ke's avatar
Guolin Ke committed
280
  TextReader<size_t> reader(weight_filename.c_str(), false);
Guolin Ke's avatar
Guolin Ke committed
281
282
283
284
  reader.ReadAllLines();
  if (reader.Lines().size() <= 0) {
    return;
  }
285
  Log::Info("Loading weights...");
Guolin Ke's avatar
Guolin Ke committed
286
287
288
  num_weights_ = static_cast<data_size_t>(reader.Lines().size());
  weights_ = new float[num_weights_];
  for (data_size_t i = 0; i < num_weights_; ++i) {
289
    double tmp_weight = 0.0f;
Guolin Ke's avatar
Guolin Ke committed
290
    Common::Atof(reader.Lines()[i].c_str(), &tmp_weight);
291
    weights_[i] = static_cast<float>(tmp_weight);
Guolin Ke's avatar
Guolin Ke committed
292
293
294
295
296
297
  }
}

void Metadata::LoadInitialScore() {
  num_init_score_ = 0;
  if (init_score_filename_[0] == '\0') { return; }
Guolin Ke's avatar
Guolin Ke committed
298
  TextReader<size_t> reader(init_score_filename_, false);
Guolin Ke's avatar
Guolin Ke committed
299
300
  reader.ReadAllLines();

301
  Log::Info("Loading initial scores...");
Guolin Ke's avatar
Guolin Ke committed
302
  num_init_score_ = static_cast<data_size_t>(reader.Lines().size());
303

304
  init_score_ = new float[num_init_score_ * num_class_];
305
  double tmp = 0.0f;
306

307
308
309
310
311
312
313
314
  if (num_class_ == 1){
      for (data_size_t i = 0; i < num_init_score_; ++i) {
        Common::Atof(reader.Lines()[i].c_str(), &tmp);
        init_score_[i] = static_cast<float>(tmp);
      }
  } else {
      std::vector<std::string> oneline_init_score;
      for (data_size_t i = 0; i < num_init_score_; ++i) {
315
        oneline_init_score = Common::Split(reader.Lines()[i].c_str(), '\t');
316
317
318
319
320
321
322
323
        if (static_cast<int>(oneline_init_score.size()) != num_class_){
            Log::Fatal("Invalid initial score file. Redundant or insufficient columns.");
        }
        for (int k = 0; k < num_class_; ++k) {
          Common::Atof(oneline_init_score[k].c_str(), &tmp);
          init_score_[k * num_init_score_ + i] = static_cast<float>(tmp);
        }
      }
Guolin Ke's avatar
Guolin Ke committed
324
325
326
327
328
329
330
331
  }
}

void Metadata::LoadQueryBoundaries() {
  num_queries_ = 0;
  std::string query_filename(data_filename_);
  // default query file name
  query_filename.append(".query");
Guolin Ke's avatar
Guolin Ke committed
332
  TextReader<size_t> reader(query_filename.c_str(), false);
Guolin Ke's avatar
Guolin Ke committed
333
334
335
336
  reader.ReadAllLines();
  if (reader.Lines().size() <= 0) {
    return;
  }
337
  Log::Info("Loading query boundaries...");
Guolin Ke's avatar
Guolin Ke committed
338
339
340
341
342
343
344
345
346
347
348
349
350
351
  query_boundaries_ = new data_size_t[reader.Lines().size() + 1];
  num_queries_ = static_cast<data_size_t>(reader.Lines().size());
  query_boundaries_[0] = 0;
  for (size_t i = 0; i < reader.Lines().size(); ++i) {
    int tmp_cnt;
    Common::Atoi(reader.Lines()[i].c_str(), &tmp_cnt);
    query_boundaries_[i + 1] = query_boundaries_[i] + static_cast<data_size_t>(tmp_cnt);
  }
}

void Metadata::LoadQueryWeights() {
  if (weights_ == nullptr || query_boundaries_ == nullptr) {
    return;
  }
352
  Log::Info("Loading query weights...");
Guolin Ke's avatar
Guolin Ke committed
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
  query_weights_ = new float[num_queries_];
  for (data_size_t i = 0; i < num_queries_; ++i) {
    query_weights_[i] = 0.0f;
    for (data_size_t j = query_boundaries_[i]; j < query_boundaries_[i + 1]; ++j) {
      query_weights_[i] += weights_[j];
    }
    query_weights_[i] /= (query_boundaries_[i + 1] - query_boundaries_[i]);
  }
}

void Metadata::LoadFromMemory(const void* memory) {
  const char* mem_ptr = reinterpret_cast<const char*>(memory);

  num_data_ = *(reinterpret_cast<const data_size_t*>(mem_ptr));
  mem_ptr += sizeof(num_data_);
  num_weights_ = *(reinterpret_cast<const data_size_t*>(mem_ptr));
  mem_ptr += sizeof(num_weights_);
  num_queries_ = *(reinterpret_cast<const data_size_t*>(mem_ptr));
  mem_ptr += sizeof(num_queries_);

  if (label_ != nullptr) { delete[] label_; }
  label_ = new float[num_data_];
  std::memcpy(label_, mem_ptr, sizeof(float)*num_data_);
Guolin Ke's avatar
Guolin Ke committed
376
  mem_ptr += sizeof(float)*num_data_;
Guolin Ke's avatar
Guolin Ke committed
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432

  if (num_weights_ > 0) {
    if (weights_ != nullptr) { delete[] weights_; }
    weights_ = new float[num_weights_];
    std::memcpy(weights_, mem_ptr, sizeof(float)*num_weights_);
    mem_ptr += sizeof(float)*num_weights_;
  }
  if (num_queries_ > 0) {
    if (query_boundaries_ != nullptr) { delete[] query_boundaries_; }
    query_boundaries_ = new data_size_t[num_queries_ + 1];
    std::memcpy(query_boundaries_, mem_ptr, sizeof(data_size_t)*(num_queries_ + 1));
    mem_ptr += sizeof(data_size_t)*(num_queries_ + 1);
  }
  if (num_weights_ > 0 && num_queries_ > 0) {
    if (query_weights_ != nullptr) { delete[] query_weights_; }
    query_weights_ = new float[num_queries_];
    std::memcpy(query_weights_, mem_ptr, sizeof(float)*num_queries_);
    mem_ptr += sizeof(float)*num_queries_;
  }
}

void Metadata::SaveBinaryToFile(FILE* file) const {
  fwrite(&num_data_, sizeof(num_data_), 1, file);
  fwrite(&num_weights_, sizeof(num_weights_), 1, file);
  fwrite(&num_queries_, sizeof(num_queries_), 1, file);
  fwrite(label_, sizeof(float), num_data_, file);
  if (weights_ != nullptr) {
    fwrite(weights_, sizeof(float), num_weights_, file);
  }
  if (query_boundaries_ != nullptr) {
    fwrite(query_boundaries_, sizeof(data_size_t), num_queries_ + 1, file);
  }
  if (query_weights_ != nullptr) {
    fwrite(query_weights_, sizeof(float), num_queries_, file);
  }

}

size_t Metadata::SizesInByte() const  {
  size_t size = sizeof(num_data_) + sizeof(num_weights_)
    + sizeof(num_queries_);
  size += sizeof(float) * num_data_;
  if (weights_ != nullptr) {
    size += sizeof(float) * num_weights_;
  }
  if (query_boundaries_ != nullptr) {
    size += sizeof(data_size_t) * (num_queries_ + 1);
  }
  if (query_weights_ != nullptr) {
    size += sizeof(float) * num_queries_;
  }
  return size;
}


}  // namespace LightGBM