I am writing a airflow task to read a large csv and save it to postgresql database. I found this asyncpg package that has a copy function which runs much faster than any other packages. However, it is async, and I don't know how to incorporate it into Airflow. Here is a sample code:
from airflow import DAG
from airflow.operators.python_operator import PythonOperator
from datetime import datetime, timedelta
from pandas import DataFrame
import asyncpg
async def to_sql(dataframe, table_name, schema_name='public', timeout=None, truncate=False):
connection = await asyncpg.connect(user='postgres', host='host.docker.internal', database='quantaxis', password='123456')
result = await connection.copy_records_to_table(
table_name,
records=dataframe.values.tolist(),
columns=shared_columns,
schema_name=schema_name,
timeout=timeout)
await connection.close()
return result
default_args = {
'owner': 'Airflow',
'depends_on_past': False,
'start_date': datetime(2020, 1, 1),
'retries': 1,
'retry_delay': timedelta(minutes=1),
}
dag = DAG('pythonexp2123', default_args=default_args, schedule_interval=timedelta(days=1))
async def save_file_to_database(ds):
df = pd.read_csv("data{0}.csv".format(ds))
r = await to_sql(df, 'test')
return r
t1 = PythonOperator(
task_id='pushing_task',
provide_context=True,
python_callable=save_file_to_database,
dag=dag
)
t1
When I run it, it will return error:
Can't Pickle Object <Corountine>
How could I change the function to make this Dag work? I still want to use asyncpg package because of its speed.
You can try running the async function in an eventloop using asyncio. If you are uing python 3.7 > you can simply call asyncio.run(async_function())
https://docs.python.org/3/library/asyncio-task.html
from airflow import DAG
from airflow.operators.python_operator import PythonOperator
from datetime import datetime, timedelta
from pandas import DataFrame
import asyncpg
import asyncio
async def to_sql(dataframe, table_name, schema_name='public', timeout=None, truncate=False):
connection = await asyncpg.connect(user='postgres', host='host.docker.internal', database='quantaxis', password='123456')
result = await connection.copy_records_to_table(
table_name,
records=dataframe.values.tolist(),
columns=shared_columns,
schema_name=schema_name,
timeout=timeout)
await connection.close()
return result
default_args = {
'owner': 'Airflow',
'depends_on_past': False,
'start_date': datetime(2020, 1, 1),
'retries': 1,
'retry_delay': timedelta(minutes=1),
}
dag = DAG('pythonexp2123', default_args=default_args, schedule_interval=timedelta(days=1))
async def save_file_to_database(ds):
df = pd.read_csv("data{0}.csv".format(ds))
r = await to_sql(df, 'test')
return r
def run_async(ds):
loop = asyncio.get_event_loop()
result = loop.run_until_complete(save_file_to_database(ds))
return result
t1 = PythonOperator(
task_id='pushing_task',
provide_context=True,
python_callable=run_async,
dag=dag
)
t1
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With