academic_observatory_workflows.openalex_telescope.telescope =========================================================== .. py:module:: academic_observatory_workflows.openalex_telescope.telescope Classes ------- .. autoapisummary:: academic_observatory_workflows.openalex_telescope.telescope.DagParams Functions --------- .. autoapisummary:: academic_observatory_workflows.openalex_telescope.telescope.create_dag Module Contents --------------- .. py:class:: DagParams(*, dag_id: str, cloud_workspace: observatory_platform.airflow.workflow.CloudWorkspace, bq_dataset_id: str = 'openalex', api_bq_dataset_id: str = 'dataset_api', entity_names: List[str] = None, schema_folder: str = project_path('openalex_telescope', 'schema'), dataset_description: str = 'The OpenAlex dataset: https://docs.openalex.org/', non_concurrent_table_expiry_days: int = 62, n_transfer_trys: int = 3, primary_key: str = 'id', aws_conn_id: str = 'aws_openalex', aws_openalex_bucket: str = 'openalex', slack_conn_id: Optional[str] = AirflowConns.SLACK, start_date: pendulum.DateTime = pendulum.datetime(2021, 12, 1), schedule: str = '@weekly', max_active_runs: int = 1, retries: int = 3, gke_image: str = DEFAULT_GKE_IMAGE, gke_namespace: str = 'coki-astro', gke_volume_path: str = '/data', gke_resource_map: dict = None, gke_volume_map: dict = None, gke_conn_id: str = 'gke_cluster', **kwargs) .. py:attribute:: dag_id .. py:attribute:: cloud_workspace .. py:attribute:: bq_dataset_id :value: 'openalex' .. py:attribute:: api_bq_dataset_id :value: 'dataset_api' .. py:attribute:: entity_names :value: None .. py:attribute:: schema_folder .. py:attribute:: dataset_description :value: 'The OpenAlex dataset: https://docs.openalex.org/' .. py:attribute:: non_concurrent_table_expiry_days :value: 62 .. py:attribute:: n_transfer_trys :value: 3 .. py:attribute:: primary_key :value: 'id' .. py:attribute:: aws_conn_id :value: 'aws_openalex' .. py:attribute:: aws_openalex_bucket :value: 'openalex' .. py:attribute:: slack_conn_id .. py:attribute:: start_date .. py:attribute:: schedule :value: '@weekly' .. py:attribute:: max_active_runs :value: 1 .. py:attribute:: retries :value: 3 .. py:attribute:: gke_conn_id :value: 'gke_cluster' .. py:attribute:: gke_params_map .. py:function:: create_dag(dag_params: DagParams) -> airflow.DAG