airflow_18_ex_simple.py

from datetime import datetime, timedelta
from airflow import DAG
from airflow.operators.bash_operator import BashOperator

default_args = {
    'owner': 'myowner',
    'depends_on_past': False,
    'start_date': datetime(year=2017, month=10, day=18, hour=0, minute=0),
    'email': ['me@example.com'],
    'email_on_failure': True,
    'email_on_retry': False,
    'retries': 0,
    'retry_delay': timedelta(minutes=10),
    'execution_timeout': timedelta(hours=2)
}
params = {
    'script': './run.sh',
    'jar': '/path/to/my.jar',
    'class': 'com.example.MyApp',
    'memory_overhead': '1024',
    'executor_cores': '4',
    'num_executors': '4',
    'driver_memory': '2g',
    'executor_memory': '15g',
    'master': 'yarn',
    'deploy_mode': 'client',
    'queue': 'myqueue',
    'log_config_file': '/path/to/log4j.properties',
    'spark_home': '/path/to/spark2-client/bin',
    'proxy_user': 'myproxyuser',
    'spark_port_max_retries': 64
}
schedule_interval = '10 0 * * * '  # Daily at 0010Hrs SGT
dag_id = 'my_dag_id'
dag = DAG(
    dag_id,
    default_args=default_args,
    schedule_interval=schedule_interval,
)
globals()[dag_id] = dag
ventures = ['']
for v in ventures:
    params['venture'] = v
    task = BashOperator(
        task_id=dag_id + '_' + v + '_task',
        bash_command=params['script'],
        params=params,
        dag=dag
    )