Skip to content

M
meta_base_code
Commit 51b7a690 authored by litaolemo's avatar litaolemo
Browse files
Options

update

parent 35910730
Hide whitespace changes
Inline Side-by-side
Showing with 25 additions and 210 deletions
task/daily_search_word_count_fix.py
View file @ 51b7a690
......@@ -72,7 +72,7 @@ spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDF
# huidu_device_id_df = spark.sql(huidu_device_id_sql)
# huidu_device_id_df.createOrReplaceTempView("dev_view")
task_list = []
task_days = 80
task_days = 3
for t in range(0, task_days):
day_num = 0 - t
......
task/high_quality_diary_analysis.py
View file @ 51b7a690
......@@ -113,70 +113,14 @@ huidu_device_id_sql = r"""
select t2.device_id from
(select distinct(first_device) as device_id from online.ml_user_history_detail where partition_date = {today_str} and substr(md5(first_device),-1) in ('8', '9', 'a', 'b') and last_active_date >= {last_30_day_str}) t2
LEFT JOIN
(
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）
WHERE partition_day='{today_str}'
union all
select distinct device_id
from dim.dim_device_user_staff --去除内网用户
)spam_pv
on spam_pv.device_id=t2.device_id
LEFT JOIN
(
SELECT partition_date,device_id
FROM
(--找出user_id当天活跃的第一个设备id
SELECT user_id,partition_date,
if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
FROM online.ml_user_updates
WHERE partition_date='{today_str}'
)t1
JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = '{today_str}'
--马甲账号/模特用户
UNION ALL
SELECT user_id
FROM ml.ml_c_ct_ui_user_dimen_d
WHERE partition_day = '{today_str}'
AND (is_puppet = 'true' or is_classifyuser = 'true')
UNION ALL
--公司内网覆盖用户
select distinct user_id
from dim.dim_device_user_staff
UNION ALL
--登陆过医生设备
SELECT distinct t1.user_id
FROM
(
SELECT user_id, v.device_id as device_id
FROM online.ml_user_history_detail
LATERAL VIEW EXPLODE(device_history_list) v AS device_id
WHERE partition_date = '{today_str}'
) t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = '{today_str}'
AND is_login_doctor = '1'
) t2
ON t1.device_id = t2.device_id
)t2
on t1.user_id=t2.user_id
group by partition_date,device_id
)dev
(
select distinct device_id
from ML.ML_D_CT_DV_DEVICECLEAN_DIMEN_D
where PARTITION_DAY = '{today_str}'
AND is_abnormal_device = 'true'
)dev
on t2.device_id=dev.device_id
WHERE spam_pv.device_id IS NULL
and dev.device_id is null
WHERE dev.device_id IS NULL
""".format(today_str=today_str, last_30_day_str=last_30_day_str)
......
task/meigou_data.py
View file @ 51b7a690
......@@ -159,69 +159,13 @@ and t3.cl_id=t4.cl_id
and t3.card_id=t4.service_id
LEFT JOIN
(
SELECT distinct device_id
FROM dim.dim_device_user_staff --去除内网用户
UNION ALL
SELECT device_id
FROM ml.ml_d_ct_dv_devicespam_d --剔除刷量设备
WHERE partition_day={partition_date}
)a
on t1.device_id=a.device_id
LEFT JOIN
(
SELECT partition_date,device_id
FROM
(--找出user_id当天活跃的第一个设备id
SELECT user_id,partition_date,
if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
FROM online.ml_user_updates
WHERE partition_date>={yesterday_str}
AND partition_date<= {partition_date}
)t1
JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = {partition_date}
--马甲账号/模特用户
UNION ALL
SELECT user_id
FROM ml.ml_c_ct_ui_user_dimen_d
WHERE partition_day = {partition_date}
AND (is_puppet = 'true' or is_classifyuser = 'true')
UNION ALL
--公司内网覆盖用户
select distinct user_id
from dim.dim_device_user_staff
UNION ALL
--登陆过医生设备
SELECT distinct t1.user_id
FROM
(
SELECT user_id, v.device_id as device_id
FROM online.ml_user_history_detail
LATERAL VIEW EXPLODE(device_history_list) v AS device_id
WHERE partition_date = {partition_date}
)t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = {partition_date}
AND is_login_doctor = '1'
)t2
ON t1.device_id = t2.device_id
)t2
on t1.user_id=t2.user_id
group by partition_date,device_id
select distinct device_id
from ML.ML_D_CT_DV_DEVICECLEAN_DIMEN_D
where PARTITION_DAY = '{start_date}'
AND is_abnormal_device = 'true'
)b
on t1.partition_date=b.partition_date and t1.device_id=b.device_id
where (a.device_id is NULL or a.device_id ='')
and (b.device_id is null or b.device_id ='')
on t1.device_id=b.device_id
where b.device_id is null or b.device_id =''
GROUP BY t1.partition_date
,grey_type,active_type,device_os_type
order by 1
......
task/recommend_strategy_fix.py
View file @ 51b7a690
......@@ -73,7 +73,7 @@ spark.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJso
spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDFArryMerge'")
for t in range(0, 60):
for t in range(0, 3):
day_num = 0 - t
now = (datetime.datetime.now() + datetime.timedelta(days=day_num))
last_30_day_str = (now + datetime.timedelta(days=-30)).strftime("%Y%m%d")
......
task/search_strategy_d.py
View file @ 51b7a690
......@@ -142,13 +142,10 @@ for t in range(0, task_days):
print("-------------------------------")
sql_spam_pv_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）
WHERE partition_day='{yesterday_str}'
UNION ALL
SELECT DISTINCT device_id
FROM dim.dim_device_user_staff
select distinct device_id
from ML.ML_D_CT_DV_DEVICECLEAN_DIMEN_D
where PARTITION_DAY = '{yesterday_str}'
AND is_abnormal_device = 'true'
""".format(yesterday_str=yesterday_str)
print(sql_spam_pv_device_id)
......
task/spark_test.py
View file @ 51b7a690
......@@ -244,16 +244,3 @@ WHERE spam_pv.device_id IS NULL
# print("-------------------------------")
# for count, res in enumerate(sql_res):
# # print(count, res)
# track = res.track
# if not track:
# continue
# track_list = track.split(",")
# for one_key_word in track_list:
# if one_key_word in res_dict:
# res_dict[one_key_word] += 1
# else:
# res_dict[one_key_word] = 1
# print(res_dict)
task/tractate_analysis_in_7000.py
View file @ 51b7a690
......@@ -110,70 +110,13 @@ huidu_device_id_sql = r"""
select t2.device_id from
(select distinct(first_device) as device_id from online.ml_user_history_detail where partition_date = {today_str} and substr(md5(first_device),-1) in ('8', '9', 'a', 'b') and last_active_date >= {last_30_day_str}) t2
LEFT JOIN
(
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）
WHERE partition_day='{today_str}'
union all
select distinct device_id
from dim.dim_device_user_staff --去除内网用户
)spam_pv
on spam_pv.device_id=t2.device_id
LEFT JOIN
(
SELECT partition_date,device_id
FROM
(--找出user_id当天活跃的第一个设备id
SELECT user_id,partition_date,
if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
FROM online.ml_user_updates
WHERE partition_date='{today_str}'
)t1
JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = '{today_str}'
--马甲账号/模特用户
UNION ALL
SELECT user_id
FROM ml.ml_c_ct_ui_user_dimen_d
WHERE partition_day = '{today_str}'
AND (is_puppet = 'true' or is_classifyuser = 'true')
UNION ALL
--公司内网覆盖用户
select distinct user_id
from dim.dim_device_user_staff
UNION ALL
--登陆过医生设备
SELECT distinct t1.user_id
FROM
(
SELECT user_id, v.device_id as device_id
FROM online.ml_user_history_detail
LATERAL VIEW EXPLODE(device_history_list) v AS device_id
WHERE partition_date = '{today_str}'
) t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = '{today_str}'
AND is_login_doctor = '1'
) t2
ON t1.device_id = t2.device_id
)t2
on t1.user_id=t2.user_id
group by partition_date,device_id
)dev
( select distinct device_id
from ML.ML_D_CT_DV_DEVICECLEAN_DIMEN_D
where PARTITION_DAY = '{start_date}'
AND is_abnormal_device = 'true') dev
on t2.device_id=dev.device_id
WHERE spam_pv.device_id IS NULL
and dev.device_id is null
WHERE dev.device_id is null
""".format(today_str=today_str,last_30_day_str=last_30_day_str)
......
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