def _create_pipeline(): """Implements the chicago taxi pipeline with TFX.""" return pipeline.Pipeline( pipeline_name=_pipeline_name, pipeline_root=_pipeline_root, components=test_utils.create_e2e_components(_data_root), enable_cache=True, metadata_connection_config=metadata.sqlite_metadata_connection_config( _metadata_path), )
def _create_pipeline(): pipeline_name = _PIPELINE_NAME pipeline_root = os.path.join(_get_test_output_dir(), pipeline_name) components = test_utils.create_e2e_components(_get_csv_input_location()) return tfx_pipeline.Pipeline( pipeline_name=pipeline_name, pipeline_root=pipeline_root, metadata_connection_config=metadata_store_pb2.ConnectionConfig(), components=components[: 2], # Run two components only to reduce overhead. log_root='/var/tmp/tfx/logs', additional_pipeline_args={ 'WORKFLOW_ID': pipeline_name, }, )
def _create_pipeline(): pipeline_name = _PIPELINE_NAME test_output_dir = 'gs://{}/test_output'.format(test_utils.BUCKET_NAME) pipeline_root = os.path.join(test_output_dir, pipeline_name) components = test_utils.create_e2e_components(pipeline_root, test_utils.DATA_ROOT, test_utils.TAXI_MODULE_FILE) return tfx_pipeline.Pipeline( pipeline_name=pipeline_name, pipeline_root=pipeline_root, metadata_connection_config=metadata_store_pb2.ConnectionConfig(), components=components[:2], log_root='/var/tmp/tfx/logs', additional_pipeline_args={ 'WORKFLOW_ID': pipeline_name, }, )
def _create_pipeline(): pipeline_name = _PIPELINE_NAME pipeline_root = os.path.join(test_utils.get_test_output_dir(), pipeline_name) components = test_utils.create_e2e_components( pipeline_root, test_utils.get_csv_input_location(), test_utils.get_transform_module(), test_utils.get_trainer_module(), ) return tfx_pipeline.Pipeline( pipeline_name=pipeline_name, pipeline_root=pipeline_root, metadata_connection_config=metadata_store_pb2.ConnectionConfig(), components=components[:4], log_root='/var/tmp/tfx/logs', additional_pipeline_args={ 'WORKFLOW_ID': pipeline_name, }, )