Function TestLearnerSerialization

tests/cpp/test_serialization.cc:150–290

void CompareJsonModels(Json l, Json r) { CompareJSON(std::move(l), std::move(r)); }

void TestLearnerSerialization(Args args, FeatureMap const& fmap, std::shared_ptr<DMatrix> p_dmat) {
  for (auto& batch : p_dmat->GetBatches<SparsePage>()) {
    batch.data.HostVector();
    batch.offset.HostVector();
  }

  int32_t constexpr kIters = 2;

  common::TemporaryDirectory tempdir;
  std::string const fname = tempdir.Str() + "/model";

  std::vector<std::string> dumped_0;
  std::string model_at_kiter;

  // Train for kIters.
  {
    std::unique_ptr<dmlc::Stream> fo(dmlc::Stream::Create(fname.c_str(), "w"));
    std::unique_ptr<Learner> learner{Learner::Create({p_dmat})};
    learner->SetParams(args);
    for (int32_t iter = 0; iter < kIters; ++iter) {
      learner->UpdateOneIter(iter, p_dmat);
    }
    dumped_0 = learner->DumpModel(fmap, true, "json");
    learner->Save(fo.get());

    common::MemoryBufferStream mem_out(&model_at_kiter);
    learner->Save(&mem_out);
  }

  // Assert dumped model is same after loading
  std::vector<std::string> dumped_1;
  {
    std::unique_ptr<dmlc::Stream> fi(dmlc::Stream::Create(fname.c_str(), "r"));
    std::unique_ptr<Learner> learner{Learner::Create({p_dmat})};
    learner->Load(fi.get());
    learner->Configure();
    dumped_1 = learner->DumpModel(fmap, true, "json");
  }
  ASSERT_EQ(dumped_0, dumped_1);

  std::string model_at_2kiter;

  // Test training continuation with data from host
  {
    std::string continued_model;
    {
      // Continue the previous training with another kIters
      std::unique_ptr<dmlc::Stream> fi(dmlc::Stream::Create(fname.c_str(), "r"));
      std::unique_ptr<Learner> learner{Learner::Create({p_dmat})};
      learner->Load(fi.get());
      learner->Configure();

      // verify the loaded model doesn't change.
      std::string serialised_model_tmp;
      common::MemoryBufferStream mem_out(&serialised_model_tmp);
      learner->Save(&mem_out);
      ASSERT_EQ(model_at_kiter, serialised_model_tmp);