# Create the DAG object
dag = DAG(dag_id="example_dag", ..., schedule_interval="0 * * * *")


# Define operations
start_cluster = StartClusterOperator(task_id="start_cluster", dag=dag)
ingest_customer_data = SparkJobOperator(task_id="ingest_customer_data", dag=dag)
ingest_product_data = SparkJobOperator(task_id="ingest_product_data", dag=dag)
enrich_customer_data = PythonOperator(task_id="enrich_customer_data", ..., dag = dag)


# Set up dependency flow
start_cluster.set_downstream(ingest_customer_data)
ingest_customer_data.set_downstream(enrich_customer_data)
ingest_product_data.set_downstream(enrich_customer_data)