How to dynamically create subdags in Airflow

Question

I have a main dag which retrieves a file and splits the data in this file to separate csv files. I have another set of tasks that must be done for each file of these csv files.

Answer 1

I tried creating subdags dynamically as follows

# create and return and DAG
def create_subdag(dag_parent, dag_id_child_prefix, db_name):
    # dag params
    dag_id_child = '%s.%s' % (dag_parent.dag_id, dag_id_child_prefix + db_name)
    default_args_copy = default_args.copy()

    # dag
    dag = DAG(dag_id=dag_id_child,
              default_args=default_args_copy,
              schedule_interval='@once')

    # operators
    tid_check = 'check2_db_' + db_name
    py_op_check = PythonOperator(task_id=tid_check, dag=dag,
                                 python_callable=check_sync_enabled,
                                 op_args=[db_name])

    tid_spark = 'spark2_submit_' + db_name
    py_op_spark = PythonOperator(task_id=tid_spark, dag=dag,
                                 python_callable=spark_submit,
                                 op_args=[db_name])

    py_op_check >> py_op_spark
    return dag

# wrap DAG into SubDagOperator
def create_subdag_operator(dag_parent, db_name):
    tid_subdag = 'subdag_' + db_name
    subdag = create_subdag(dag_parent, tid_prefix_subdag, db_name)
    sd_op = SubDagOperator(task_id=tid_subdag, dag=dag_parent, subdag=subdag)
    return sd_op

# create SubDagOperator for each db in db_names
def create_all_subdag_operators(dag_parent, db_names):
    subdags = [create_subdag_operator(dag_parent, db_name) for db_name in db_names]
    # chain subdag-operators together
    airflow.utils.helpers.chain(*subdags)
    return subdags


# (top-level) DAG & operators
dag = DAG(dag_id=dag_id_parent,
          default_args=default_args,
          schedule_interval=None)

subdag_ops = create_subdag_operators(dag, db_names)

Note that the list of inputs for which subdags are created, here db_names, can either be declared statically in the python file or could be read from external source.

The resulting DAG looks like this

Diving into SubDAG(s)