1

I am trying to trigger an airflow DAG externally and passing some parameters to the DAG. The DAG is scheduled to run every 3 minutes. My problem is that the parameters are only being used by the first DAG run.

from pyexpat import model
from airflow import DAG
from datetime import datetime, timedelta
from airflow.operators.python import PythonOperator

import os

dag_id = "proj"
home_path = os.path.expanduser("~")
runpath = os.path.join(home_path, "airflow/data", dag_id)


def load_data(ti):
    import os

    train = os.path.join(runpath, "mnist")
    test = os.path.join(runpath, "mnist.t")
    model = os.path.join(runpath, "trained.mnist")

    if not os.path.exists(train):
        os.system(
            "curl https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/mnist.bz2 --output mnist.bz2"
        )
        os.system("bzip2 -d mnist.bz2")

    if not os.path.exists(test):
        os.system(
            "curl https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/multiclass/mnist.t.bz2 --output mnist.t.bz2"
        )
        os.system("bzip2 -d mnist.t.bz2")

    ti.xcom_push(key="train_path", value=train)
    ti.xcom_push(key="test_path", value=test)
    ti.xcom_push(key="model_path", value=model)


def train(
    **context,
):
    import os

    ti = context["ti"]

    train = ti.xcom_pull(task_ids="load_data", key="train_path")
    model_path = ti.xcom_pull(task_ids="load_data", key="model_path")

    lr = context["dag_run"].conf["lr"]
    epochs = context["dag_run"].conf["epochs"]
    name = context["dag_run"].conf["name"]

    print(lr)
    print(epochs)

    ti.xcom_push(key="model_name", value=model_final_name)


def validate(**context):
    ti = context["ti"]

    test = ti.xcom_pull(task_ids="load_data", key="test_path")
    model_path = ti.xcom_pull(task_ids="train", key="model_name")
    print(test)
    print(model_path)

with DAG(
    dag_id="project",
    default_args={"owner": "airflow"},
    start_date=datetime(2022, 8, 8),
    schedule_interval=timedelta(minutes=3),
    tags=["mnist_4"],
    catchup=False,
) as dag:

    print(runpath)

    os.makedirs(runpath, exist_ok=True)
    os.chdir(runpath)

    read_file = PythonOperator(
        task_id="load_data",
        python_callable=load_data,
        provide_context=True,
    )

    process_train = PythonOperator(
        task_id="train",
        python_callable=train,
        provide_context=True,
    )

    validate = PythonOperator(
        task_id="validate", python_callable=validate, provide_context=True
    )


read_file >> process_train >> validate

I trigger dag with the command

airflow dags trigger project --conf '{"epochs":1,"name":"trial_3","lr":0.001}'

Except one run, all the other runs have failed with the following error: KeyError: 'lr'

When I look at the conf for the dag runs, only one run has the conf, rest are empty.

If I look at the field External Trigger, only one run is true which means while triggering the dag, only run is triggered, rest are scheduled.

I want to know how to pass config to the scheduled dags as well.

shubh gupta
  • 94
  • 7

1 Answers1

1

I hope it can help.

Indeed dag run conf works for manual triggered DAGs, in this case the conf can be passed.

For sheduled DAGs, you can set default params in your DAGs, this post shows an example :

Airflow how to set default values for dag_run.conf

Mazlum Tosun
  • 5,761
  • 1
  • 9
  • 23