Airflow Cheat Sheet

from airflow.decorators import dag, taskfrom datetime import datetime@dag(schedule='@daily', start_date=datetime(2024, 1, 1), catchup=False)def etl_pipeline():    @task    def extract():        return {'rows': 100}    @task    def transform(data):        data['rows'] *= 2        return data    @task    def load(data):        print(f"Loaded {data['rows']} rows")    load(transform(extract()))etl_pipeline()

from airflow import DAGfrom airflow.operators.python import PythonOperatorfrom airflow.operators.bash import BashOperatorfrom datetime import datetimewith DAG('classic_dag', start_date=datetime(2024, 1, 1), schedule='0 6 * * *') as dag:    t1 = BashOperator(task_id='print_date', bash_command='date')    t2 = PythonOperator(task_id='say_hi', python_callable=lambda: print('hi'))    t1 >> t2   # t1 must run before t2

airflow webserver -p 8080              # Start the UIairflow scheduler                      # Start the schedulerairflow dags list                      # List all DAGsairflow dags trigger etl_pipeline      # Manually trigger a DAG runairflow tasks test etl_pipeline extract 2024-01-01   # Test a single task