Airflow: Dynamically derive dag_id to be called from another DAG - airflow

I am trying to derive name of the DAG to be called in another DAG dynamically. In the following task "trigger_transform_dag" fails to execute. Can you please help me with deriving the dag id for task 'trigger_transform_dag' dynamically
default_args = {
'owner': 'airflow',
'depends_on_past': False,
'email': ['airflow#example.com'],
'email_on_failure': False,
'email_on_retry': False,
'retries': 1,
'retry_delay': timedelta(minutes=5),
'start_date': airflow.utils.dates.days_ago(0),
}
def run_dag(**context):
file_path='ABC'
context['ti'].xcom_push(key = 'key1', value = file_path)
return 1
def check_file_name(**context):
pulled_value_1 = context['ti'].xcom_pull(task_ids = 'run_dataflow_template',key = 'key1')
if pulled_value_1 = 'ABC':
push_value = 'sample1'
return push_value
else:
push_value = 'sample2'
return push_value
return pulled_value_1
with DAG('sample',
default_args=default_args,
schedule_interval='10 * * * *',
start_date=datetime(2017, 3, 20),
max_active_runs=1,
catchup=False) as dag:
t1 = PythonOperator(
task_id='run_dataflow_template',
provide_context=True,
python_callable=run_dag
)
t2 = TriggerDagRunOperator(
task_id="trigger_transform_dag",
provide_context=True,
trigger_dag_id=check_file_name()
)
end = DummyOperator(
trigger_rule='one_success',
task_id='end')
t1 >> t2 >> end

I don't know if there is a simpler way, but you can create a custom operator that takes inspiration from the TriggerDagRunOperator (https://github.com/apache/airflow/blob/master/airflow/operators/dagrun_operator.py) and uses the passed Callable to get the function.
Something I hacked together really quick (can be definitely improved):
from airflow.models import DAG
from airflow.utils.dates import days_ago, timedelta
from airflow.operators.dagrun_operator import TriggerDagRunOperator
import random
import datetime
from typing import Dict, Optional, Union, Callable
from airflow.api.common.experimental.trigger_dag import trigger_dag
from airflow.models import BaseOperator
from airflow.utils import timezone
from airflow.utils.decorators import apply_defaults
class TriggerDagRunWithFuncOperator(BaseOperator):
"""
Triggers a DAG run for a specified ``dag_id``
:param trigger_dag_id_f: the dag_id function to trigger
:type trigger_dag_id_f: Callable
:param conf: Configuration for the DAG run
:type conf: dict
:param execution_date: Execution date for the dag (templated)
:type execution_date: str or datetime.datetime
"""
template_fields = ("execution_date", "conf")
ui_color = "#ffefeb"
#apply_defaults
def __init__(
self,
get_dag_name_f: Callable,
conf: Optional[Dict] = None,
execution_date: Optional[Union[str, datetime.datetime]] = None,
*args,
**kwargs
) -> None:
super().__init__(*args, **kwargs)
self.conf = conf
self.get_dag_name_f = get_dag_name_f
if not isinstance(execution_date, (str, datetime.datetime, type(None))):
raise TypeError(
"Expected str or datetime.datetime type for execution_date."
"Got {}".format(type(execution_date))
)
self.execution_date: Optional[datetime.datetime] = execution_date # type: ignore
def execute(self, context: Dict):
if isinstance(self.execution_date, datetime.datetime):
run_id = "trig__{}".format(self.execution_date.isoformat())
elif isinstance(self.execution_date, str):
run_id = "trig__{}".format(self.execution_date)
self.execution_date = timezone.parse(self.execution_date) # trigger_dag() expects datetime
else:
run_id = "trig__{}".format(timezone.utcnow().isoformat())
dag_id_to_call = self.get_dag_name_f()
# Ignore MyPy type for self.execution_date because it doesn't pick up the timezone.parse() for strings
trigger_dag(
dag_id=dag_id_to_call,
run_id=run_id,
conf=self.conf,
execution_date=self.execution_date,
replace_microseconds=False,
)
args={
'owner': 'arocketman',
'start_date': days_ago(1)
}
dag = DAG(dag_id='dyna_dag', default_args=args, schedule_interval=None)
def your_function():
return 'my_sample_dag'
with dag:
run_this_task = TriggerDagRunWithFuncOperator(
task_id='run_this',
get_dag_name_f=your_function
)

Related

Airflow setting conditional dependency

Hello I am trying to set conditional dependency in Airflow, in the below flow my objective is to run print-conf-success only after successful execution of print-conf-1 and print-conf-2 and print-conf-failure in either of them fails. In the below dependency I setup upstream as a list of [print-conf-2, print-conf-1] expecting it to have both the task as upstream however instead of having both the tasks as upstream its coming as downstream for each of them. What is the correct way to set dependency for having both having success status for [print-conf-2, print-conf-1] for task print-conf-success and failure for either of them for task print-conf-failure
"""Example DAG demonstrating the usage of the PythonOperator."""
import time
from pprint import pprint
from datetime import datetime
from airflow.utils.trigger_rule import TriggerRule
from airflow import DAG
from airflow.operators.python import PythonOperator, PythonVirtualenvOperator
DEFAULT_ARGS = {
'owner': 'admin',
'depends_on_past': False,
'start_date': datetime(2022, 5, 20, 0),
'retries': 2
}
def print_log(**kwargs):
print("--------------------")
print("1, 2, 3")
print("--------------------")
def print_log_failed(**kwargs):
print("--------------------")
print("1, 2, 3, failed")
print("--------------------")
with DAG(dag_id="test_dag", schedule_interval=None, default_args=DEFAULT_ARGS, max_active_runs=10) as dag:
log_conf = PythonOperator(
task_id='print-conf-success',
provide_context=True,
python_callable=print_log,
trigger_rule=TriggerRule.ALL_SUCCESS,
dag=dag)
log_conf_failure = PythonOperator(
task_id='print-conf-failure',
provide_context=True,
python_callable=print_log,
trigger_rule=TriggerRule.ALL_SUCCESS,
dag=dag)
log_conf_1 = PythonOperator(
task_id='print-conf-1',
provide_context=True,
python_callable=print_log,
trigger_rule=TriggerRule.ALL_SUCCESS,
dag=dag)
log_conf_2 = PythonOperator(
task_id='print-conf-2',
provide_context=True,
python_callable=print_log,
trigger_rule=TriggerRule.ALL_SUCCESS,
dag=dag)
log_conf_3 = PythonOperator(
task_id='print-conf-3',
provide_context=True,
python_callable=print_log_failed,
trigger_rule=TriggerRule.ONE_FAILED,
dag=dag)
log_conf.set_upstream([log_conf_1, log_conf_2])
log_conf_failure.set_upstream([log_conf_1, log_conf_2])
log_conf_3 >> ([log_conf_1, log_conf_2])
I think this is what you are after:
print-conf-1, print-conf-2, print-conf-3 can be successful or fail (for demonstration in the code below print-conf-3 will always fail).
print-conf-failure will be executed only if at least 1 upstream task has failed.
print-conf-failure will be executed only if all upstream tasks are successful.
code:
from datetime import datetime
from airflow.utils.trigger_rule import TriggerRule
from airflow import DAG, AirflowException
from airflow.operators.python import PythonOperator
DEFAULT_ARGS = {
'owner': 'admin',
'depends_on_past': False,
'start_date': datetime(2022, 5, 20, 0),
'retries': 2
}
def print_log(**kwargs):
print("--------------------")
print("1, 2, 3")
print("--------------------")
def print_log_failed(**kwargs):
print("--------------------")
print("1, 2, 3, failed")
print("--------------------")
raise AirflowException("failing")
with DAG(dag_id="example_test_dag", schedule_interval=None, default_args=DEFAULT_ARGS, max_active_runs=10) as dag:
log_conf = PythonOperator(
task_id='print-conf-success',
provide_context=True, # Remove this line if you are on Airflow 2
python_callable=print_log)
log_conf_failure = PythonOperator(
task_id='print-conf-failure',
provide_context=True, # Remove this line if you are on Airflow 2
python_callable=print_log,
trigger_rule=TriggerRule.ONE_FAILED)
log_conf_1 = PythonOperator(
task_id='print-conf-1',
provide_context=True, # Remove this line if you are on Airflow 2
python_callable=print_log)
log_conf_2 = PythonOperator(
task_id='print-conf-2',
provide_context=True, # Remove this line if you are on Airflow 2
python_callable=print_log)
log_conf_3 = PythonOperator(
task_id='print-conf-3',
provide_context=True, # Remove this line if you are on Airflow 2
python_callable=print_log_failed)
[log_conf_1, log_conf_2] >> log_conf
[log_conf_1, log_conf_2, log_conf_3] >> log_conf_failure

Airflow trigger dag with config

I try to use configs in dag using "trigger w/config".
def execute(**kwargs):
dag_run = kwargs['dag_run']
start_date = dag_run.conf['start_dt'] if 'start_dt' in dag_run.conf.keys() else kwargs['start_dt']
end_date = dag_run.conf['end_dt'] if 'end_dt' in dag_run.conf.keys() else kwargs['end_dt']
print(f'start_date = {start_date}, end_date = {end_date}')
dag = DAG(
"corp_dev_ods_test_dag",
default_args=default_args,
description='DAG',
schedule_interval='10 1 * * *',
start_date=days_ago(0),
#params={'dt' : '{{ macros.ds_add(ds, -7) }}'},
catchup=False,
tags=['dev']
)
run_submit = PythonVirtualenvOperator(
task_id='run_submit',
requirements=dag_requirements,
python_callable=execute,
system_site_packages=False,
dag=dag,
op_kwargs={'start_dt' : '{{ macros.ds_add(ds, -7) }}', 'end_dt': '{{ macros.ds_add(ds, -7) }}'}
)
run_submit
I got "KeyError": kwargs["dag_run"]. But in case of PythonOperator (Instead of PythonVirtualenvOperator) it works.
So, how can I use such parameters in my dag?
You need to provide an empty params variable in your task, for example:
from airflow.decorators import dag, task
from datetime import datetime
default_params = {"start_date": "2022-01-01", "end_date": "2022-12-01"}
#dag(
schedule=None,
start_date=datetime(2021, 1, 1),
catchup=False,
tags=['using_params'],
params=default_params
)
def mydag():
#task
def extract(params={}):
import helper
filenames = helper.extract(start=params.get("start_date"))
return filenames
extract()
_dag = mydag()
Now in the UI when you Trigger DAG w/ config you should be able to see and change the default params. And be able to access it in your dag task.

Airflow dynamically genarated task not run in order

I have created dynamic tasks generation dag. Tasks are generated accurately, But those tasks are not trigger in order,not work in consistently.
i have noticed it triggered on alphanumeric order.
Let's check run_modification_ tasks. i have generated 0 to 29 tasks. i have noticed it trigger on below format.
run_modification_0
run_modification_1
run_modification_10
run_modification_11
run_modification_12
run_modification_13
run_modification_14
run_modification_15
run_modification_16
run_modification_17
run_modification_18
run_modification_19
run_modification_2
run_modification_21
run_modification_23....
But i need to run it on tasks order like
run_modification_0
run_modification_1
run_modification_2
run_modification_3
run_modification_4
run_modification_5..
Please help me to run those tasks on task created order.
from datetime import date, timedelta, datetime
from airflow.utils.dates import days_ago
from airflow.models import DAG
from airflow.operators.python_operator import PythonOperator
from airflow.operators.bash_operator import BashOperator
from airflow.operators.postgres_operator import PostgresOperator
from airflow.hooks.postgres_hook import PostgresHook
from airflow.models import Variable
import os
args = {
'owner': 'Airflow',
'start_date': days_ago(2),
}
dag = DAG(
dag_id='tastOrder',
default_args=args,
schedule_interval=None,
tags=['task']
)
modification_processXcom = """ cd {{ ti.xcom_pull(task_ids=\'run_modification_\'+params.i, key=\'taskDateFolder\') }} """
def modificationProcess(ds,**kwargs):
today = datetime.strptime('2021-01-01', '%Y-%m-%d').date()
i = str(kwargs['i'])
newDate = today-timedelta(days=int(i))
print(str(newDate))
kwargs["ti"].xcom_push("taskDateFolder", str(newDate))
def getDays():
today = today = datetime.strptime('2021-01-01', '%Y-%m-%d').date()
yesterday = today - timedelta(days=30)
day_Diff = today-yesterday
return day_Diff,today
day_Diff, today = getDays()
for i in reversed(range(0,day_Diff.days)):
run_modification = PythonOperator(
task_id='run_modification_'+str(i),
provide_context=True,
python_callable=modificationProcess,
op_kwargs={'i': str(i)},
dag=dag,
)
modification_processXcom = BashOperator(
task_id='modification_processXcom_'+str(i),
bash_command=modification_processXcom,
params = {'i' :str(i)},
dag = dag
)
run_modification >> modification_processXcom
To get the dependency as:
run_modification_1 -> modification_processXcom_1 ->
run_modification_2 -> modification_processXcom_2 -> ... - >
run_modification_29 -> modification_processXcom_29
You can do:
from datetime import datetime
from airflow import DAG
from airflow.operators.bash import BashOperator
dag = DAG(
dag_id='my_dag',
schedule_interval=None,
start_date=datetime(2021, 8, 10),
catchup=False,
is_paused_upon_creation=False,
)
mylist1 = []
mylist2 = []
for i in range(1, 30):
mylist1.append(
BashOperator( # Replace with your requested operator
task_id=f'run_modification_{i}',
bash_command=f"""echo executing run_modification_{i}""",
dag=dag,
)
)
mylist2.append(
BashOperator( # Replace with your requested operator
task_id=f'modification_processXcom_{i}',
bash_command=f"""echo executing modification_processXcom_{i}""",
dag=dag,
)
)
if len(mylist1) > 0:
mylist1[-1] >> mylist2[-1] # This set dependency between run_modifiation to modification_processXcom
if len(mylist1) > 1:
mylist2[-2] >> mylist1[-1] # This set dependency between modification_processXcom to previous run_modifiation
This code create a list of operators and set them to run one after another as:
Tree view:

How to trigger a task in airflow if immediate parent task fails?

What i am mainly aiming for is that the restore_denormalized_es_Data should only get triggered when the load_denormalized_es_data task fails. If the load_denormalized_es_data task is successful then the command should be directed to end . Here as you can see , my restore is working when archive fails and load is skipped or retrying as a result i am getting wrong answers.
Have stated the code i am using
import sys
import os
from datetime import datetime
#import files what u want to import
# Airflow level imports
from airflow.models import DAG
from airflow.operators.dummy_operator import DummyOperator
from airflow.operators.python_operator import PythonOperator,BranchPythonOperator
from airflow.operators.bash_operator import BashOperator
from airflow.utils.trigger_rule import TriggerRule
#Imported all the functions and the code is able to call the functions with ease
# Name of the Dag
DAG_NAME = "DAG"
#Default arguments
default_args = {
"owner": "Mehul",
"start_date": datetime.today().strftime("%Y-%m-%d"),
"provide_context": True
}
# Define the dag object
dag = DAG(
DAG_NAME,
default_args=default_args,
schedule_interval=None
)
archive_denormalized_es_data = PythonOperator(
task_id = "archive_denormalized_es_data",
python_callable = archive_current_ES_data,
trigger_rule=TriggerRule.ALL_SUCCESS,
provide_context = False,
dag=dag
)
load_denormalized_es_data = PythonOperator(
task_id = "load_denormalized_es_data",
python_callable = es_load,
provide_context = False,
trigger_rule = TriggerRule.ALL_SUCCESS,
dag=dag
)
restore_denormalized_es_data = PythonOperator(
task_id = "restore_denormalized_es_data",
python_callable = restore_current_ES_data,
trigger_rule=TriggerRule.ALL_FAILED,
provide_context=False,
dag=dag
)
END = DummyOperator(
task_id="END",
trigger_rule=TriggerRule.ALL_SUCCESS,
dag=dag)
denormalized_data_creation>>archive_denormalized_es_data>>load_denormalized_es_data
load_denormalized_es_data<<archive_denormalized_es_data<<denormalized_data_creation
load_denormalized_es_data>>restore_denormalized_es_data
restore_denormalized_es_data<<load_denormalized_es_data
load_denormalized_es_data>>END
END<<load_denormalized_es_data
restore_denormalized_es_data>>END
END<<restore_denormalized_es_data
Here is the picture of the pipelines referred above
If I understand correctly, you want to skip the rest of the pipeline if A fails.
ShortCircuitOperator will allow Airflow to short circuit (skip) the rest of the pipeline.
Here is an example that does what you outlined.
from datetime import datetime
from airflow.models import DAG
from airflow.operators.dummy import DummyOperator
from airflow.operators.python import PythonOperator, ShortCircuitOperator
from airflow.utils.trigger_rule import TriggerRule
from airflow.utils.state import State
def proceed(**context):
ti = context['dag_run'].get_task_instance(a.task_id)
if ti.state == State.FAILED:
return False
else:
return True
dag = DAG(
dag_id="dag",
start_date=datetime(2021, 4, 5),
schedule_interval='#once',
)
with dag:
a = PythonOperator(
task_id='archive_denormalized_es_data',
python_callable=lambda x: 1
)
gate = ShortCircuitOperator(
task_id='gate',
python_callable=proceed,
trigger_rule=TriggerRule.ALL_DONE
)
b = PythonOperator(
task_id='load_denormalized_es_data',
python_callable=lambda: 1
)
c = DummyOperator(
task_id='restore_denormalized_es_data',
trigger_rule=TriggerRule.ALL_FAILED
)
d = DummyOperator(
task_id='END',
trigger_rule=TriggerRule.ONE_SUCCESS
)
a >> gate >> b >> c
[b, c] >> d
If archive_denormalized_es_data fails, the rest of the pipeline is skipped, meaning Airflow does not run restore_denormalized_es_data
If load_denormalized_es_data fails, restore_denormalized_es_data runs and continues to END.
If load_denormalized_es_data succeeds, restore_denormalized_es_data is skipped and continues to END.
You code is essentially missing the logic to skip when archive_denormalized_es_data fails, which the ShortCircuitOperator takes care of for you.

Create multiple task in airflow using loop

I want to create task which will be update columns rows and send mail for every line in data table. At the moment I create task which download the data from main table. I cannot create tasks for every line in temp data table. Could you tell what I doing wrong and how I can generate and run tasks in lopp?
from datetime import datetime, timedelta
import airflow
from airflow import DAG
from airflow.contrib.operators.bigquery_operator import BigQueryOperator
from airflow.contrib.operators.bigquery_get_data import BigQueryGetDataOperator
from airflow.contrib.operators.bigquery_check_operator import BigQueryValueCheckOperator
from airflow.operators import PythonOperator
from airflow.operators.python_operator import PythonOperator
default_args = {
'owner': 'cmap',
'depends_on_past': False,
'start_date': airflow.utils.dates.days_ago(0),
'email_on_failure': False,
'email_on_retry': False,
'retries': 0,
'retry_delay': timedelta(minutes=5),
}
with DAG('dq_bigquery_test',
max_active_runs=1,
schedule_interval='#once',
catchup=False,
default_args=default_args) as dag:
query = "SELECT * from `dbce-bi-prod-e6fd.dev_dataquality.data_logging_inc` where MailRequired = false"
insert = "INSERT into dbce-bi-prod-e6fd.dev_dataquality.data_logging_inc (DataTimeStamp, Robot, Status) Values (CURRENT_TIMESTAMP(), 'TestRobot', 'Test')"
my_bq_task = BigQueryOperator(
task_id='query_exc_on_teste',
sql=query,
write_disposition='WRITE_TRUNCATE',
create_disposition='CREATE_IF_NEEDED',
bigquery_conn_id='google_cloud_dbce_bi_prod',
use_legacy_sql=False,
destination_dataset_table='dev_dataquality.testTable')
get_data = BigQueryGetDataOperator(
task_id='get_data_from_query',
project_id='dbce-bi-prod-e6fd',
dataset_id='dev_dataquality',
table_id='testTable',
max_results='100',
selected_fields='Robot,Status,MailRequired',
bigquery_conn_id='google_cloud_dbce_bi_prod'
)
def process_data_from_bq(**kwargs):
ti = kwargs['ti']
update_column = []
bq_data = ti.xcom_pull(task_ids='get_data_from_query')
print(bq_data)
# Now bq_data here would have your data in Python list
for index, i in enumerate(bq_data):
update_query = "UPDATE `dbce-bi-prod-e6fd.dev_dataquality.data_logging_inc` SET MailSent = True WHERE Robot = '{}'".format(i[0])
print(update_query)
update_column.append(BigQueryOperator(
task_id='update_column_{}'.format(index),
sql=update_query,
write_disposition='WRITE_EMPTY',
create_disposition='CREATE_IF_NEEDED',
bigquery_conn_id='google_cloud_dbce_bi_prod',
use_legacy_sql=False,
dag=dag
))
if index not in [0]:
update_column[index-1] >> update_column[index]
process_data = PythonOperator(
task_id='process_data_from_bq',
python_callable=process_data_from_bq,
provide_context=True
)
my_bq_task >> get_data >> process_data
Thank you for your help!

Resources