python连接hive批量补充时间分区特征

1. python连接数据库

from pyhive import hive

conn = hive.Connection(
        host= 'xxx xxx', 
        port= xxx, 
        auth='CUSTOM',
        username='your user name', 
        password='your password',
        database='default')
cursor = conn.cursor()

2. SQL代码封装

设计为可传参方式

def get_sql(d):
    d = "'"+ d + "'"
    add_sql_horizon = """
    CREATE table tmp.horizon_feature as
    with 
    tmp_dlr_cstm as(
        select dealer_id,
        sum(
            case when DateDiff("""+d+""",created_time)<=30 and date_from not in (0,3) then 1
            else 0
            end
        ) as pcust_acc_1m_dlr_off
        from dcs.nt_tp_p_customers
        group by dealer_id
    )

    select   
        nvl(cast(d1.dealer_id as str