Umang Mistry
89 lines
2.5 KiB
Python
89 lines
2.5 KiB
Python
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from datetime import datetime
|
|
import logging
|
|
|
|
from airflow import DAG
|
|
from airflow.providers.snowflake.operators.snowflake import SnowflakeOperator
|
|
from airflow.providers.snowflake.hooks.snowflake import SnowflakeHook
|
|
from airflow.operators.python import PythonOperator
|
|
from airflow.utils.trigger_rule import TriggerRule
|
|
from airflow.operators.empty import EmptyOperator
|
|
from airflow.models import Variable
|
|
from airflow.exceptions import AirflowFailException
|
|
|
|
|
|
logging.basicConfig(level=logging.INFO)
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
|
|
SNOWFLAKE_CONN_ID = "doczy_dev_snowflake"
|
|
DAG_ID = "load_training_results"
|
|
DATABASE="DOCZY_DEV"
|
|
# bucket = "airflow-data-ingestion"
|
|
|
|
TAGS=["dev","training_interface","dataload"]
|
|
|
|
# Trigger rules
|
|
ALL_SUCCESS = 'all_success'
|
|
ALL_FAILED = 'all_failed'
|
|
ALL_DONE = 'all_done'
|
|
ONE_SUCCESS = 'one_success'
|
|
ONE_FAILED = 'one_failed'
|
|
|
|
# This will be replaced with the payload from the event after API connection is setup
|
|
training_results_file_name = "training_results_sample.csv"
|
|
attempt_logs_file_name = "attempt_logs_sample.csv"
|
|
|
|
|
|
def call_stored_proc(proc_name,file_name):
|
|
dwh_hook = SnowflakeHook(snowflake_conn_id=SNOWFLAKE_CONN_ID)
|
|
with dwh_hook.get_conn() as conn:
|
|
# dwh_hook.set_autocommit(conn,autocommit=False)
|
|
cur = conn.cursor()
|
|
|
|
cur.execute(f"CALL {DATABASE}.STG.{proc_name}('{file_name}');")
|
|
result = cur.fetchone()
|
|
if result[0] == 'Setup, Load, and Audit Complete':
|
|
logger.info('PROCEDURE EXECUTED SUCCESSFULLY')
|
|
else:
|
|
raise AirflowFailException("Check the DAG logs for more information. ERROR FROM SNOWFLAKE: ", result)
|
|
logger.info(f"QUERY EXECUTION RESULT: {str(result)}")
|
|
|
|
dag = DAG(
|
|
DAG_ID,
|
|
start_date=datetime(2024, 1, 1),
|
|
default_args={"snowflake_conn_id": SNOWFLAKE_CONN_ID, "retries":0},
|
|
tags=TAGS,
|
|
catchup=False,
|
|
schedule=None
|
|
)
|
|
|
|
begin_job = EmptyOperator(task_id='Begin')
|
|
|
|
|
|
load_training_results = PythonOperator(
|
|
task_id="load_training_results",
|
|
python_callable=call_stored_proc,
|
|
dag=dag,
|
|
op_kwargs={'proc_name':'LOAD_TRAINING_RESULTS', 'file_name':training_results_file_name}
|
|
)
|
|
|
|
load_attempt_logs_sp = PythonOperator(
|
|
task_id="load_attempt_logs",
|
|
python_callable=call_stored_proc,
|
|
dag=dag,
|
|
op_kwargs={'proc_name':'LOAD_ATTEMPT_LOGS', 'file_name':attempt_logs_file_name}
|
|
)
|
|
|
|
|
|
|
|
|
|
end_job = EmptyOperator(task_id='End')
|
|
|
|
|
|
begin_job >> load_training_results >> load_attempt_logs_sp >> end_job |