Basic querying example

.env

HIVE_HOST=my.location.com
HIVE_USERNAME=user.name
HIVE_PASSWORD=my_passWord

environment.yml

name: my_env
channels:
  - conda-forge
dependencies:
  - pip
  - ipykernel
  - "pandas<1.1"
  - python-dotenv
  - pip:
      - thrift-sasl~=0.4.2
      - impyla~=0.16

load.py

import os
from impala.dbapi import connect
from dotenv import load_dotenv
import pandas as pd

load_dotenv(override=True)

conn = connect(
    host=os.getenv("HIVE_HOST"),
    port=21050,
    auth_mechanism='PLAIN',
    use_ssl=True,
    user=os.getenv("HIVE_USERNAME"), 
    password=os.getenv("HIVE_PASSWORD"),
)

cursor = conn.cursor()

with open("my_query.sql", "r") as f:
    query = " ".join(f.readlines())
    
df = pd.read_sql(
    query,
    conn
)
print(df)