Last active
January 28, 2021 09:15
-
-
Save TimmyCarbone/958aaa08fbe6281f4bf4d98fd6fce1de to your computer and use it in GitHub Desktop.
Example of dbt scheduling with Airflow
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# How to schedule dbt runs with Airflow using gocardless/airflow-dbt | |
# Folder structure is as such: | |
# | |
# /app | |
# /airflow | |
# /dags | |
# /dbt_dag.py | |
# /dbt | |
# /config | |
# /profiles.yml | |
# /models | |
# /web | |
# /traffic.py | |
from airflow import DAG | |
from airflow_dbt.operators.dbt_operator import DbtRunOperator | |
default_args = { | |
'owner': 'airflow', | |
'depends_on_past': False, | |
'start_date': '2020-01-01', | |
'email': ['email@example.com'], | |
'email_on_failure': False, | |
'email_on_retry': False, | |
'retries': 1, | |
'retry_delay': timedelta(minutes=5), | |
'dbt_dir': dbt_path | |
} | |
dbt_path = dbt_path = os.environ['DBT_PATH'] # /app/dbt | |
# Use a cron schedule in `schedule_interval`, here it will run every 20 minutes | |
dag = DAG(dag_id='update_models', default_args=default_args, schedule_interval='*/20 * * * *', catchup=False) | |
# DbtRunOperator from gocardless/airflow-dbt | |
# This will run the /app/dbt/models/web/traffic.py dbt model | |
dbt_run = DbtRunOperator( | |
task_id='dbt_update_models', | |
profiles_dir=dbt_path + '/config', # The folder where is profiles.yml (/app/dbt/config) | |
dir=dbt_path, | |
queue='airflow_queue_1', | |
models='web.traffic', | |
dag=dag | |
) | |
# Airflow dependency graph (with a single task here) | |
dbt_run |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment