def test_pipeline_runner_build_datasets(sample_ids, tiny_files_structure):
runner = PipelineRunner(file_structure=tiny_files_structure, )
X_train, y_train, X_val, y_val = runner.build_datasets(
BenchmarkDataset(), sample_ids[:-2], sample_ids[-2:])
assert X_train.any()
assert X_val.any()
assert y_train.any()
assert y_val.any()
def test_pipeline_runner_run_calls(tiny_files_structure, sample_ids):
runner = PipelineRunner(file_structure=tiny_files_structure, )
runner.ds_builder = Mock(spec=DatasetBuilder)
runner.model_trainer = Mock(spec=ModelTrainer)
runner.get_model_path = Mock(spec=runner.get_model_path)
runner.build_datasets = Mock(spec=runner.build_datasets,
return_value=(0, 0, 0, 0))
runner.splitter.split = Mock(spec=runner.splitter.split,
return_value=(0, 0))
runner.evaluate_validation_set = Mock(spec=runner.evaluate_validation_set)
runner.run_pipeline(
sample_ids,
dataset=BenchmarkDataset(),
model=BenchmarkModel(),
)
runner.splitter.split.assert_called_once_with(sample_ids, 0.2)
runner.build_datasets.assert_called_once()
runner.get_model_path.assert_called_once()
runner.model_trainer.train_model.assert_called_once()
runner.evaluate_validation_set.assert_called_once()