pyspark-mysql.sh

?

CREATE EXTERNAL TABLE welly.transactions_1k
STORED AS KUDU
TBLPROPERTIES (
  'kudu.table_name' = 'transactions_1k'
);

CREATE EXTERNAL TABLE welly.customers
STORED AS KUDU
TBLPROPERTIES (
  'kudu.table_name' = 'customers'
);

CREATE EXTERNAL TABLE welly.gasstations
STORED AS KUDU
TBLPROPERTIES (
  'kudu.table_name' = 'gasstations'
);

CREATE EXTERNAL TABLE welly.products
STORED AS KUDU
TBLPROPERTIES (
  'kudu.table_name' = 'products'
);

https://github.com/hackathonBI/CCS

https://github.com/hackathonBI/CCS/blob/master/Tasks.md

!pip install impyla

from impala.dbapi import connect
from impala.util import as_pandas

conn = connect(host='178.128.112.105', port=21050) 
cursor = conn.cursor()
cursor.execute('SELECT * FROM welly.transactions_1k LIMIT 100')
df = as_pandas(cursor)

df.head()