Skip to content

M
meta_base_code
Commit 1419dd88 authored by litaolemo's avatar litaolemo
Browse files
Options

update

parent 2b9bfa3b
Hide whitespace changes
Inline Side-by-side
Showing with 56 additions and 59 deletions
task/search_strategy_d.py
View file @ 1419dd88
...@@ -81,65 +81,62 @@ for t in range(0, task_days): ...@@ -81,65 +81,62 @@ for t in range(0, task_days):
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 = """ sql_distinct_device_id = """
( SELECT DISTINCT device_id
SELECT DISTINCT device_id FROM ml.ml_d_ct_dv_devicespam_d --去除机构刷单设备，即作弊设备（浏览和曝光事件去除）
FROM ml.ml_d_ct_dv_devicespam_d --去除机构刷单设备，即作弊设备（浏览和曝光事件去除） WHERE partition_day={yesterday_str}
WHERE partition_day={yesterday_str}
UNION ALL
UNION ALL SELECT DISTINCT device_id
SELECT DISTINCT device_id FROM dim.dim_device_user_staff --去除内网用户
FROM dim.dim_device_user_staff --去除内网用户 LEFT JOIN
)spam_pv (
on spam_pv.device_id=t1.cl_id SELECT partition_date,device_id
LEFT JOIN FROM
( (--找出user_id当天活跃的第一个设备id
SELECT partition_date,device_id SELECT user_id,partition_date,
FROM if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
(--找出user_id当天活跃的第一个设备id FROM online.ml_user_updates
SELECT user_id,partition_date, WHERE partition_date>='${{yesterday_str}}' AND partition_date<'${{today_str}}'
if(size(device_list) > 0, device_list [ 0 ], '') AS device_id )t1
FROM online.ml_user_updates JOIN
WHERE partition_date>='${{yesterday_str}}' AND partition_date<'${{today_str}}' ( --医生账号
)t1 SELECT distinct user_id
JOIN FROM online.tl_hdfs_doctor_view
( --医生账号 WHERE partition_date = {yesterday_str}
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view --马甲账号/模特用户
WHERE partition_date = {yesterday_str} UNION ALL
SELECT user_id
--马甲账号/模特用户 FROM ml.ml_c_ct_ui_user_dimen_d
UNION ALL WHERE partition_day = {yesterday_str}
SELECT user_id AND (is_puppet = 'true' or is_classifyuser = 'true')
FROM ml.ml_c_ct_ui_user_dimen_d
WHERE partition_day = {yesterday_str} UNION ALL
AND (is_puppet = 'true' or is_classifyuser = 'true') --公司内网覆盖用户
select distinct user_id
UNION ALL from dim.dim_device_user_staff
--公司内网覆盖用户
select distinct user_id UNION ALL
from dim.dim_device_user_staff --登陆过医生设备
SELECT distinct t1.user_id
UNION ALL FROM
--登陆过医生设备 (
SELECT distinct t1.user_id SELECT user_id, v.device_id as device_id
FROM FROM online.ml_user_history_detail
( LATERAL VIEW EXPLODE(device_history_list) v AS device_id
SELECT user_id, v.device_id as device_id WHERE partition_date = {yesterday_str}
FROM online.ml_user_history_detail )t1
LATERAL VIEW EXPLODE(device_history_list) v AS device_id JOIN
WHERE partition_date = {yesterday_str} (
)t1 SELECT device_id
JOIN FROM online.ml_device_history_detail
( WHERE partition_date = {yesterday_str}
SELECT device_id AND is_login_doctor = '1'
FROM online.ml_device_history_detail )t2
WHERE partition_date = {yesterday_str} ON t1.device_id = t2.device_id
AND is_login_doctor = '1' )t2
)t2 on t1.user_id=t2.user_id
ON t1.device_id = t2.device_id group by partition_date,device_id
)t2
on t1.user_id=t2.user_id
group by partition_date,device_id
)dev """.format(yesterday_str=yesterday_str,today_str=today_str) )dev """.format(yesterday_str=yesterday_str,today_str=today_str)
print(sql_distinct_device_id) print(sql_distinct_device_id)
distinct_device_id_df = spark.sql(sql_distinct_device_id,) distinct_device_id_df = spark.sql(sql_distinct_device_id,)
......
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