Load initial scores with binary data files in CLI version (#4807)

docs/Parameters.rst

@@ -1269,6 +1269,8 @@ The initial score file corresponds with data file line by line, and has per scor
 And if the name of data file is ``train.txt``, the initial score file should be named as ``train.txt.init`` and placed in the same folder as the data file.
 In this case, LightGBM will auto load initial score file if it exists.
 
+If binary data files exist for raw data file ``train.txt``, for example in the name ``train.txt.bin``, then the initial score file should be named as ``train.txt.bin.init``.
+
 Weight Data
 ~~~~~~~~~~~
 

include/LightGBM/dataset.h

@@ -147,6 +147,9 @@ class Metadata {
     queries_[idx] = static_cast<data_size_t>(value);
   }
 
+  /*! \brief Load initial scores from file */
+  void LoadInitialScore(const std::string& data_filename);
+
   /*!
   * \brief Get weights, if not exists, will return nullptr
   * \return Pointer of weights
@@ -223,8 +226,6 @@ class Metadata {
   #endif  // USE_CUDA_EXP
 
  private:
-  /*! \brief Load initial scores from file */
-  void LoadInitialScore();
   /*! \brief Load wights from file */
   void LoadWeights();
   /*! \brief Load query boundaries from file */

src/io/dataset_loader.cpp

@@ -272,6 +272,11 @@ Dataset* DatasetLoader::LoadFromFile(const char* filename, int rank, int num_mac
     is_load_from_binary = true;
     Log::Info("Load from binary file %s", bin_filename.c_str());
     dataset.reset(LoadFromBinFile(filename, bin_filename.c_str(), rank, num_machines, &num_global_data, &used_data_indices));
+
+    // checks whether there's a initial score file when loaded from binary data files
+    // the intial score file should with suffix ".bin.init"
+    dataset->metadata_.LoadInitialScore(bin_filename);
+
     dataset->device_type_ = config_.device_type;
     dataset->gpu_device_id_ = config_.gpu_device_id;
     #ifdef USE_CUDA_EXP
@@ -338,6 +343,9 @@ Dataset* DatasetLoader::LoadFromFileAlignWithOtherDataset(const char* filename,
   } else {
     // load data from binary file
     dataset.reset(LoadFromBinFile(filename, bin_filename.c_str(), 0, 1, &num_global_data, &used_data_indices));
+    // checks whether there's a initial score file when loaded from binary data files
+    // the intial score file should with suffix ".bin.init"
+    dataset->metadata_.LoadInitialScore(bin_filename);
   }
   // not need to check validation data
   // check meta data

src/io/metadata.cpp

@@ -29,7 +29,7 @@ void Metadata::Init(const char* data_filename) {
   LoadQueryBoundaries();
   LoadWeights();
   LoadQueryWeights();
-  LoadInitialScore();
+  LoadInitialScore(data_filename_);
 }
 
 Metadata::~Metadata() {
@@ -418,10 +418,10 @@ void Metadata::LoadWeights() {
   weight_load_from_file_ = true;
 }
 
-void Metadata::LoadInitialScore() {
+void Metadata::LoadInitialScore(const std::string& data_filename) {
   num_init_score_ = 0;
-  std::string init_score_filename(data_filename_);
-  init_score_filename = std::string(data_filename_);
+  std::string init_score_filename(data_filename);
+  init_score_filename = std::string(data_filename);
   // default init_score file name
   init_score_filename.append(".init");
   TextReader<size_t> reader(init_score_filename.c_str(), false);