Airflow connect to sql server select results to a data frame - airflow

Question

Airflow-pandas-read-sql-query to dataframe
i am trying to connect to SQL server local to get data from a table and process the data using pandas operations but i m failing to figure out how to pass the select query results to a data frame
the below works to clear data in the table
``` sql_command = """ DELETE FROM [TestDB].[dbo].[PythonTestData] """
t3 = MsSqlOperator( task_id = 'run_test_proc',
mssql_conn_id = 'mssql_local',
sql = sql_command,
dag = dag,
database = 'TestDB',
autocommit = True) ```
the intended pandas is
query = 'SELECT * FROM [ClientData] '#where product_name='''+i+''''''
df = pd.read_sql(query, conn)
pn_list = df['ClientID'].tolist()
#print("The original pn_list is : " + str(pn_list))
for i in pn_list:
varw= str(i)
queryw = 'SELECT * FROM [ClientData] where [ClientID]='''+varw+''
dfw = pd.read_sql(queryw, conn)
dfw = dfw.applymap(str)
cols=['product_id','product_name','brand_id']
x=dfw.values.tolist()
x=x[0]
ClientID=x[0]
Name=x[1]
Org=x[2]
Email=x[3]
#print('Name :'+Name+' ,'+'Org :'+Org+' ,'+'Email :'+Email+' ,'+'ClientID :'+ClientID)
salesData_qry= 'SELECT * FROM [TestDB].[dbo].[SalesData] where [ClientID]='''+ClientID+''
salesData_df= pd.read_sql(salesData_qry, conn)
salesData_df['year1'] = salesData_df['Order Date'].dt.strftime('%Y')
salesData_df['OrderMonth'] = salesData_df['Order Date'].dt.strftime('%b')
filename ='Daily_Campaign_Report_'+Name+'_'+Org+'_'+datetime.now().strftime("%Y%m%d_%H%M%S")
p = Path('C:/Users/user/Documents/WorkingData/')
salesData_df.to_csv(Path(p, filename + '.csv'))```
Please point me to correct approach as i m new to airflow

Answer 1

I'm not so clear on how you generate the query code but in order to get dataframe from MsSQL you need to use MsSqlHook:
from airflow.providers.microsoft.mssql.hooks.mssql import MsSqlHook
def mssql_func(**kwargs):
hook = MsSqlHook(conn_id='mssql_local')
df = hook.get_pandas_df(sql="YOUR_QUERY")
#do whatever you need on the df
run_this = PythonOperator(
task_id='mssql_task',
python_callable=mssql_func,
dag=dag
)

Answer 2

this is the code i am using for the dag
def mssql_func(**kwargs):
conn = MsSqlHook.get_connection(conn_id="mssql_local")
hook = conn.get_hook()
df = hook.get_pandas_df(sql="SELECT * FROM [TestDB].[dbo].[ClientData]")
#do whatever you need on the df
print(df)
run_this = PythonOperator(
task_id='mssql_task',
python_callable=mssql_func,
dag=dag
)
Error Log
[2021-01-12 16:07:15,114] {providers_manager.py:159} WARNING - The provider for package 'apache-airflow-providers-imap' could not be registered from because providers for that package name have already been registered
[2021-01-12 16:07:15,618] {base.py:65} INFO - Using connection to: id: mssql_local. Host: localhost, Port: 1433, Schema: dbo, Login: sa, Password: XXXXXXXX, extra: None
[2021-01-12 16:07:15,626] {taskinstance.py:1396} ERROR - (18456, b"Login failed for user 'sa'.DB-Lib error message 20018, severity 14:\nGeneral SQL Server error: Check messages from the SQL Server\nDB-Lib error message 20002, severity 9:\nAdaptive Server connection failed (localhost)\nDB-Lib error message 20002, severity 9:\nAdaptive Server connection failed (localhost)\n")
Traceback (most recent call last):
File "src/pymssql.pyx", line 636, in pymssql.connect
File "src/_mssql.pyx", line 1964, in _mssql.connect
File "src/_mssql.pyx", line 682, in _mssql.MSSQLConnection.__init__
File "src/_mssql.pyx", line 1690, in _mssql.maybe_raise_MSSQLDatabaseException
_mssql.MSSQLDatabaseException: (18456, b"Login failed for user 'sa'.DB-Lib error message 20018, severity 14:\nGeneral SQL Server error: Check messages from the SQL Server\nDB-Lib error message 20002, severity 9:\nAdaptive Server connection failed (localhost)\nDB-Lib error message 20002, severity 9:\nAdaptive Server connection failed (localhost)\n")