example-python-read-and-write-from-impala

import ibis
import pandas as pd
import os

# ====== Connection ======
# Connecting to Impala by providing Impala host ip and port (21050 by default) and a Webhdfs client
hdfs = ibis.hdfs_connect(host=os.environ['IP_HDFS'], port=50070)
client = ibis.impala.connect(host=os.environ['IP_IMPALA'], port=21050, hdfs_client=hdfs)

# ====== Writing table ======
# Creating a simple pandas DataFrame with two columns
liste_hello = ['hello1','hello2']
liste_world = ['world1','world2']
df = pd.DataFrame(data = {'hello' : liste_hello, 'world': liste_world})

# Writing Dataframe to Impala if table name doesn't exist
db = client.database('default')
if not client.exists_table('helloworld'):
    db.create_table('helloworld', df)
    t = db['helloworld']
    t.execute()
    
    
# ====== Reading table ======
# Selecting data with a SQL query
#limit=None to get the whole table, otherwise will only get 10000 first lines
requete = client.sql('select * from helloworld')
df = requete.execute(limit=None)