Commit b22b9fb7 authored by litaolemo's avatar litaolemo

update

parent fd53a1cc
...@@ -71,9 +71,7 @@ for t in range(0, task_days): ...@@ -71,9 +71,7 @@ for t in range(0, task_days):
today_str = now.strftime("%Y%m%d") today_str = now.strftime("%Y%m%d")
yesterday_str = (now + datetime.timedelta(days=-1)).strftime("%Y%m%d") yesterday_str = (now + datetime.timedelta(days=-1)).strftime("%Y%m%d")
one_week_age_str = (now + datetime.timedelta(days=-7)).strftime("%Y%m%d") one_week_age_str = (now + datetime.timedelta(days=-7)).strftime("%Y%m%d")
sql_distinct_device_id = r""" sql_distinct_device_id = """SELECT partition_date,device_id FROM
SELECT partition_date,device_id
FROM
( (
SELECT user_id,partition_date, SELECT user_id,partition_date,
if(size(device_list) > 0, device_list [ 0 ], '') AS device_id if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
...@@ -114,8 +112,7 @@ for t in range(0, task_days): ...@@ -114,8 +112,7 @@ for t in range(0, task_days):
)t2 )t2
ON t1.device_id = t2.device_id ON t1.device_id = t2.device_id
)t2 )t2
on t1.user_id=t2.user_id on t1.user_id=t2.user_id group by partition_date,device_id
group by partition_date,device_id
""".format(today_str=today_str, yesterday_str=yesterday_str, ) """.format(today_str=today_str, yesterday_str=yesterday_str, )
distinct_device_id_df = spark.sql(sql_distinct_device_id) distinct_device_id_df = spark.sql(sql_distinct_device_id)
distinct_device_id_df.show(1, False) distinct_device_id_df.show(1, False)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment