Commit 26739b20 authored by 魏艺敏's avatar 魏艺敏

push codes

parent 4734938d
demo=示例程序-demo
demo_bak=示例程序-demo_bak
demo_param=带参数的示例程序
demo_java=JAVA实例程序
meigou_detail_page=美购详情页来源与分发
meigou_detail_page_dispense_pv=美购详情页分发pv
meigou_detail_page_dispense_uv=美购详情页分发uv
meigou_detail_page_source_pv=美购详情页来源pv
meigou_detail_page_source_uv=美购详情页来源uv
daily_content_data=内容日报-新
search_click_path=分搜索入口的搜索框点击数据
search_input_type=分搜索方式近7天数据
search_result_click_rate=分搜索词转化率数据
search_related=分搜索方式及搜索词日报
daily_recommend_strategy=首页推荐策略日报
#step1_1.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_device_day_active_status
\ No newline at end of file
#step1_10.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online tl_hdfs_answer_view
\ No newline at end of file
#step1_11.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online tl_hdfs_topicreply_view
\ No newline at end of file
#step1_12.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online tl_hdfs_answer_reply_view
\ No newline at end of file
#step1_13.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online tl_hdfs_api_tractate_reply_view
\ No newline at end of file
#step1_14.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive al al_pm_ct_dv_deviceappversionrollbackfrom20190101_d
\ No newline at end of file
#step1_2.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online bl_hdfs_maidian_updates
\ No newline at end of file
#step1_3.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_device_updates
\ No newline at end of file
#step1_4.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_user_updates
\ No newline at end of file
#step1_5.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online bl_hdfs_operation_updates
\ No newline at end of file
#step1_6.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online tl_hdfs_api_tractate_view
\ No newline at end of file
#step1_7.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online tl_hdfs_diary_view
\ No newline at end of file
#step1_8.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online tl_hdfs_problem_view
\ No newline at end of file
#step1_9.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online tl_hdfs_question_view
\ No newline at end of file
#step2.job
type=command
dependencies=step1_1,step1_2,step1_3,step1_4,step1_5,step1_6,step1_7,step1_8,step1_9,step1_10,step1_11,step1_12,step1_13,step1_14
command=/home/bi/bi-report/lib/shell/hive.sh daily_content_data_insert
\ No newline at end of file
#step3.job
type=command
dependencies=step2
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive pm tl_pm_content_d
\ No newline at end of file
#step4.job
type=command
dependencies=step3
command=curl -X GET http://localhost:8553/api/report/sendEmail/liudi@igengmei.com,wangxin@igengmei.com,malinxi@igengmei.com,dengguangyu@igengmei.com/weiyimin@igengmei.com,zhaojianwei@igengmei.com,zhaofei@igengmei.com,yindanlei@igengmei.com/daily_content_data
\ No newline at end of file
#step1_1.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_device_day_active_status
\ No newline at end of file
#step1_2.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_community_precise_exposure_detail
\ No newline at end of file
#step1_3.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online bl_hdfs_maidian_updates
\ No newline at end of file
#step1_4.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive ml ml_d_ct_dv_devicespam_d
\ No newline at end of file
#step1_5.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_user_updates
\ No newline at end of file
#step1_6.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online tl_hdfs_doctor_view
\ No newline at end of file
#step1_7.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive ml ml_c_ct_ui_user_dimen_d
\ No newline at end of file
#step1_8.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_user_history_detail
\ No newline at end of file
#step1_9.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_device_history_detail
\ No newline at end of file
#step2.job
type=command
dependencies=step1_1,step1_2,step1_3,step1_4,step1_5,step1_6,step1_7,step1_8,step1_9
command=/home/bi/bi-report/lib/shell/hive.sh daily_recommend_strategy_insert
\ No newline at end of file
#step3.job
type=command
dependencies=step2
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive pm tl_pm_recommend_strategy_d
\ No newline at end of file
#step4.job
type=command
dependencies=step3
command=curl -X GET http://localhost:8553/api/report/sendEmail/liudi@igengmei.com,wangxin@igengmei.com,liweirui@igengmei.com,duanyingrong@igengmei.com,xuepengfei@igengmei.com,dengguangyu@igengmei.com,zhaowei@igengmei.com,songke@igengmei.com/zhaofei@igengmei.com,yindanlei@igengmei.com,weiyimin@igengmei.com,zhaojianwei@igengmei.com/daily_recommend_strategy
\ No newline at end of file
#step.job
type=command
command=/home/bi/bi-report/lib/shell/hive.sh demo
\ No newline at end of file
#step1_1.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online bl_hdfs_maidian_updates
\ No newline at end of file
#step1_2.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_device_day_active_status
\ No newline at end of file
#step1_3.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive ml ml_d_ct_dv_devicespam_d
\ No newline at end of file
#step2.job
type=command
dependencies=step1_1,step1_2,step1_3
command=curl -X GET http://localhost:8553/api/report/sendEmail/liudi@igengmei.com,wangxin@igengmei.com,zhaofei@igengmei.com/weiyimin@igengmei.com,yindanlei@igengmei.com,zhaojianwei@igengmei.com/meigou_detail_page
\ No newline at end of file
#step1_1.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_device_day_active_status
\ No newline at end of file
#step1_2.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_device_history_detail
\ No newline at end of file
#step1_3.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online bl_hdfs_maidian_updates
\ No newline at end of file
#step1_4.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive ml ml_d_ct_dv_devicespam_d
\ No newline at end of file
#step1_5.job
type=command
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive online ml_community_precise_exposure_detail
\ No newline at end of file
#step2.job
type=command
dependencies=step1_1,step1_2,step1_3,step1_4,step1_5
command=/home/bi/bi-report/lib/shell/hive.sh search_related_insert
\ No newline at end of file
#step3-1.job
type=command
dependencies=step2
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive pm tl_pm_search_click_path_d
\ No newline at end of file
#step3-2.job
type=command
dependencies=step2
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive pm tl_pm_search_input_type_d
\ No newline at end of file
#step3-3.job
type=command
dependencies=step2
command=sh /home/bi/bi-report/lib/shell/waitsuccess.sh hive pm tl_pm_search_result_click_rate_d
\ No newline at end of file
#step4.job
type=command
dependencies=step3_1,step3_2,step3_3
command=curl -X GET http://localhost:8553/api/report/sendEmail/liudi@igengmei.com,wangxin@igengmei.com,malinxi@igengmei.com,duanyingrong@igengmei.com,dengguangyu@igengmei.com/zhaofei@igengmei.com,yindanlei@igengmei.com,weiyimin@igengmei.com,zhaojianwei@igengmei.com/search_related
\ No newline at end of file
#!/bin/bash
# 定义变量方便修改
#hive="/opt/spark/spark-2.4.5-bin-hadoop2.7/bin/beeline -u jdbc:hive2://bj-gm-prod-cos-datacenter003:10010 -n data"
hive="/opt/hive/hive-1.1.0-cdh5.16.1/bin/beeline -u jdbc:hive2://bj-gm-prod-cos-datacenter005:10000 -n data"
# 如果是输入的日期按照取输入日期;如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
partition_day=$1
else
partition_day=`date --date="-1 day" +%Y%m%d`
fi
sql="
SET mapreduce.job.queuename=data;
SET mapreduce.map.memory.mb=8192;
SET mapreduce.map.java.opts=-Xmx8000m;
SET mapreduce.reduce.memory.mb=8192;
SET mapreduce.reduce.java.opts=-Xmx8000m;
set hive.auto.convert.join=true;
SET mapred.reduce.tasks=20;
SET role admin;
INSERT OVERWRITE TABLE pm.tl_pm_content_d PARTITION (PARTITION_DAY = $partition_day)
SELECT
T1.partition_date AS day_id
,T1.device_os_type AS device_os_type
,T1.active_type AS active_type
,T1.channel AS is_ai_channel
,COALESCE(T1.dau,0) AS dau
,COALESCE(T2.neirong_uv,0) AS content_uv
,COALESCE(T2.neirong_pv,0) AS content_pv
,COALESCE(ROUND(T2.neirong_uv/T1.dau,2),0) AS per_content_uv
,COALESCE(ROUND(T2.neirong_pv/T2.neirong_uv,2),0) AS per_content_pv
,COALESCE(CONCAT(ROUND(T4.retention_num1/T2.neirong_uv*100,2),'%'),0) AS retention_1
,COALESCE(CONCAT(ROUND(T4.retention_num7/T2.neirong_uv*100,2),'%'),0) AS retention_7
,COALESCE(CONCAT(ROUND(T4.retention_num30/T2.neirong_uv*100,2),'%'),0) AS retention_30
,COALESCE(T5.app_duration,0) AS avg_app_duration
,COALESCE(T3.neirong_stay,0) AS avg_content_stay
,COALESCE(T5.avg_opentimes,0) AS avg_open_times
,COALESCE(T9.search_stay,0) AS search_related_stay
,COALESCE(T9.welfare_stay,0) AS welfare_stay
,COALESCE(T9.question_stay,0) AS content_question_stay
,COALESCE(T9.ai_related_stay,0) AS ai_related_stay
,COALESCE(T9.diary_stay,0) AS content_diary_stay
,COALESCE(T9.home_stay,0) AS home_stay
,COALESCE(T9.conv_stay,0) AS conv_related_stay
,COALESCE(ROUND(T6.recommend_uv/T2.neirong_uv,2),0) AS recommend_rate
,COALESCE(ROUND(T6.recommend_pv/T6.recommend_uv,2),0) AS per_recommend_pv
,COALESCE(ROUND(T6.feeds_uv/T2.neirong_uv,2),0) AS feeds_rate
,COALESCE(ROUND(T6.feeds_pv/T6.feeds_uv,2),0) AS per_feeds_pv
,COALESCE(ROUND(T6.search_uv/T2.neirong_uv,2),0) AS search_rate
,COALESCE(ROUND(T6.search_pv/T6.search_uv,2),0) AS per_search_pv
,COALESCE(ROUND(T6.zone_uv/T2.neirong_uv,2),0) AS zone_rate
,COALESCE(ROUND(T6.zone_pv/T6.zone_uv,2),0) AS per_zone_pv
,COALESCE(ROUND(T6.content_uv/T2.neirong_uv,2),0) AS content_rate
,COALESCE(ROUND(T6.content_pv/T6.content_uv,2),0) AS per_from_content_pv
,COALESCE(ROUND(T6.blank_uv/T2.neirong_uv,2),0) AS blank_rate
,COALESCE(ROUND(T6.blank_pv/T6.blank_uv,2),0) AS per_blank_pv
,COALESCE(ROUND(T6.comment_uv/T2.neirong_uv,2),0) AS comment_rate
,COALESCE(ROUND(T6.comment_pv/T6.comment_uv,2),0) AS per_comment_pv
,COALESCE(ROUND(T6.org_uv/T2.neirong_uv,2),0) AS org_rate
,COALESCE(ROUND(T6.org_pv/T6.org_uv,2),0) AS per_org_pv
,COALESCE(ROUND(T6.category_uv/T2.neirong_uv,2),0) AS category_rate
,COALESCE(ROUND(T6.category_pv/T6.category_uv,2),0) AS per_category_pv
,COALESCE(ROUND(T6.my_diary_uv/T2.neirong_uv,2),0) AS my_diary_rate
,COALESCE(ROUND(T6.my_diary_pv/T6.my_diary_uv,2),0) AS per_my_diary_pv
,COALESCE(ROUND(T6.ai_uv/T2.neirong_uv,2),0) AS ai_rate
,COALESCE(ROUND(T6.ai_pv/T6.ai_uv,2),0) AS per_ai_pv
,null AS create_topic_num
,null AS create_reply_num
,COALESCE(T2.diary_uv,0) AS diary_uv
,COALESCE(T2.diary_pv,0) AS diary_pv
,COALESCE(ROUND(T2.diary_uv/T2.neirong_uv,2),0) AS diary_rate
,COALESCE(ROUND(T2.diary_pv/T2.diary_uv,2),0) AS per_diary_pv
,COALESCE(T3.diary_stay,0) AS diary_stay
,COALESCE(T2.post_uv,0) AS post_uv
,COALESCE(T2.post_pv,0) AS post_pv
,COALESCE(ROUND(T2.post_uv/T2.neirong_uv,2),0) AS post_rate
,COALESCE(ROUND(T2.post_pv/T2.post_uv,2),0) AS per_post_pv
,COALESCE(T3.post_stay,0) AS post_stay
,COALESCE(T2.question_uv,0) AS question_uv
,COALESCE(T2.question_pv,0) AS question_pv
,COALESCE(ROUND(T2.question_uv/T2.neirong_uv,2),0) AS question_rate
,COALESCE(ROUND(T2.question_pv/T2.question_uv,2),0) AS per_question_pv
,COALESCE(T3.question_stay,0) AS question_stay
,COALESCE(T2.question_answer_uv,0) AS question_answer_uv
,COALESCE(T2.question_answer_pv,0) AS question_answer_pv
,COALESCE(ROUND(T2.question_answer_uv/T2.neirong_uv,2),0) AS question_answer_rate
,COALESCE(ROUND(T2.question_answer_pv/T2.question_answer_uv,2),0) AS per_question_answer_pv
,COALESCE(T3.question_answer_stay,0) AS question_answer_stay
,COALESCE(T2.answer_uv,0) AS answer_uv
,COALESCE(T2.answer_pv,0) AS answer_pv
,COALESCE(ROUND(T2.answer_uv/T2.neirong_uv,2),0) AS answer_rate
,COALESCE(ROUND(T2.answer_pv/T2.answer_uv,2),0) AS per_answer_pv
,COALESCE(T3.answer_stay,0) AS answer_stay
,COALESCE(T2.video_uv,0) AS video_uv
,COALESCE(T2.video_pv,0) AS video_pv
,COALESCE(ROUND(T2.video_uv/T2.neirong_uv,2),0) AS video_rate
,COALESCE(ROUND(T2.video_pv/T2.video_uv,2),0) AS per_video_pv
,COALESCE(T3.video_stay,0) AS video_stay
,COALESCE(T2.wiki_uv,0) AS wiki_uv
,COALESCE(T2.wiki_pv,0) AS wiki_pv
,COALESCE(ROUND(T2.wiki_uv/T2.neirong_uv,2),0) AS wiki_rate
,COALESCE(ROUND(T2.wiki_pv/T2.wiki_uv,2),0) AS per_wiki_pv
,COALESCE(T3.wiki_stay,0) AS wiki_stay
,COALESCE(T2.article_uv,0) AS article_uv
,COALESCE(T2.article_pv,0) AS article_pv
,COALESCE(ROUND(T2.article_uv/T2.neirong_uv,2),0) AS article_rate
,COALESCE(ROUND(T2.article_pv/T2.article_uv,2),0) AS per_article_pv
,COALESCE(T3.article_stay,0) AS article_stay
FROM
(--基础维度/dau
SELECT partition_date,device_os_type,active_type,t2.channel,count(distinct device_id) AS dau
FROM
(
SELECT partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY partition_date,device_os_type,active_type,t2.channel
)T1
LEFT JOIN
(--内容uv/pv
SELECT partition_date
,device_os_type
,active_type
,t4.channel
,count(cl_id) as neirong_pv
,count(distinct cl_id) as neirong_uv
,count(CASE WHEN page_name IN ('diary_detail','topic_detail') THEN cl_id END) AS diary_pv
,count(distinct CASE WHEN page_name IN ('diary_detail','topic_detail') THEN cl_id END) AS diary_uv
,count(CASE WHEN page_name IN ('post_detail','user_post_detail','doctor_post_detail') THEN cl_id END) AS post_pv
,count(distinct CASE WHEN page_name IN ('post_detail','user_post_detail','doctor_post_detail') THEN cl_id END) AS post_uv
,count(CASE WHEN page_name ='question_detail' THEN cl_id END) AS question_pv
,count(distinct CASE WHEN page_name ='question_detail' THEN cl_id END) AS question_uv
,count(CASE WHEN page_name ='question_answer_detail' THEN cl_id END) AS question_answer_pv
,count(distinct CASE WHEN page_name ='question_answer_detail' THEN cl_id END) AS question_answer_uv
,count(CASE WHEN page_name='answer_detail' THEN cl_id END) AS answer_pv
,count(distinct CASE WHEN page_name='answer_detail' THEN cl_id END) AS answer_uv
,count(CASE WHEN page_name='video_steep' THEN cl_id END) AS video_pv
,count(distinct CASE WHEN page_name='video_steep' THEN cl_id END) AS video_uv
,count(CASE WHEN page_name='article_detail' THEN cl_id END) AS article_pv
,count(distinct CASE WHEN page_name='article_detail' THEN cl_id END) AS article_uv
,count(CASE WHEN page_name IN ('wiki_detail','product_detail','wiki_brand','wiki_collect') THEN cl_id END) AS wiki_pv
,count(distinct CASE WHEN page_name IN ('wiki_detail','product_detail','wiki_brand','wiki_collect') THEN cl_id END) AS wiki_uv
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t2.page_name
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(
SELECT partition_date,page_name,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
)t3
LATERAL VIEW explode(t3.channel) t4 AS channel
GROUP BY partition_date,device_os_type,active_type,t4.channel
)T2
ON T1.partition_date=T2.partition_date
AND T1.device_os_type=T2.device_os_type
AND T1.active_type=T2.active_type
AND T1.channel=T2.channel
LEFT JOIN
(--内容浏览时长
SELECT partition_date
,device_os_type
,active_type
,t4.channel
,round(sum(page_stay)/count(distinct cl_id)/60,4) as neirong_stay
,round(sum(CASE WHEN page_name IN ('diary_detail','topic_detail') THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name IN ('diary_detail','topic_detail') THEN cl_id END)/60,4) AS diary_stay
,round(sum(CASE WHEN page_name IN ('post_detail','user_post_detail','doctor_post_detail') THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name IN ('post_detail','user_post_detail','doctor_post_detail') THEN cl_id END)/60,4) AS post_stay
,round(sum(CASE WHEN page_name ='question_detail' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='question_detail' THEN cl_id END)/60,4) AS question_stay
,round(sum(CASE WHEN page_name ='question_answer_detail' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='question_answer_detail' THEN cl_id END)/60,4) AS question_answer_stay
,round(sum(CASE WHEN page_name ='answer_detail' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='answer_detail' THEN cl_id END)/60,4) AS answer_stay
,round(sum(CASE WHEN page_name ='video_steep' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='video_steep' THEN cl_id END)/60,4) AS video_stay
,round(sum(CASE WHEN page_name ='article_detail' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='article_detail' THEN cl_id END)/60,4) AS article_stay
,round(sum(CASE WHEN page_name IN ('wiki_detail','product_detail','wiki_brand','wiki_collect') THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name IN ('wiki_detail','product_detail','wiki_brand','wiki_collect') THEN cl_id END)/60,4) AS wiki_stay
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t2.page_name,t2.page_stay
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(
SELECT partition_date,page_name,cl_id,page_stay
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
AND page_stay>=0 AND page_stay<1000
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
)t3
LATERAL VIEW explode(t3.channel) t4 AS channel
GROUP BY partition_date,device_os_type,active_type,t4.channel
)T3
ON T1.partition_date=T3.partition_date
AND T1.device_os_type=T3.device_os_type
AND T1.active_type=T3.active_type
AND T1.channel=T3.channel
LEFT JOIN
(--内容用户留存
SELECT regexp_replace(partition_date,'-','') AS partition_date
,device_os_type,active_type,t5.channel
,int(count(DISTINCT CASE WHEN date_add(partition_date,1) = retention_date THEN device_id END)) AS retention_num1
,int(count(DISTINCT CASE WHEN date_add(partition_date,6) = retention_date THEN device_id END)) AS retention_num7
,int(count(DISTINCT CASE WHEN date_add(partition_date,29) = retention_date THEN device_id END)) AS retention_num30
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t3.device_id,t3.partition_date as retention_date
FROM
(
SELECT
concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(--内容用户
SELECT cl_id
,concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) AS partition_date
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
GROUP BY cl_id,concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2))
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
LEFT JOIN
(--活跃设备
SELECT device_id
,concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) AS partition_date
FROM online.ml_device_day_active_status
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
)t3
ON t2.cl_id=t3.device_id
WHERE spam_pv.device_id IS NULL
)t4
LATERAL VIEW explode(t4.channel) t5 AS channel
GROUP BY regexp_replace(partition_date,'-',''),device_os_type,active_type,t5.channel
)T4
ON T1.partition_date=T4.partition_date
AND T1.device_os_type=T4.device_os_type
AND T1.active_type=T4.active_type
AND T1.channel=T4.channel
LEFT JOIN
(--内容用户单设备app时长(m)
SELECT partition_date
,device_os_type
,active_type
,t5.channel
,round(sum(use_duration)/count(distinct cl_id)/60,4) as app_duration
,round(avg(open_times),4) as avg_opentimes
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t3.use_duration,t3.open_times
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(--内容用户
SELECT partition_date,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
GROUP BY partition_date,cl_id
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
LEFT JOIN
(
SELECT partition_date,device_id,use_duration,open_times
FROM online.ml_device_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND use_duration > 0 and use_duration < 86400
)t3
on t2.partition_date=t3.partition_date
AND t2.cl_id=t3.device_id
WHERE spam_pv.device_id IS NULL
)t4
LATERAL VIEW explode(t4.channel) t5 AS channel
GROUP BY partition_date,device_os_type,active_type,t5.channel
)T5
ON T1.partition_date=T5.partition_date
AND T1.device_os_type=T5.device_os_type
AND T1.active_type=T5.active_type
AND T1.channel=T5.channel
LEFT JOIN
(--不同来源进入内容uv/pv
SELECT partition_date
,device_os_type
,active_type
,t4.channel
,count(CASE WHEN referrer='search' THEN cl_id END) AS search_pv
,count(distinct CASE WHEN referrer='search' THEN cl_id END) AS search_uv
,count(CASE WHEN referrer='zone_v3' THEN cl_id END) AS zone_pv
,count(distinct CASE WHEN referrer='zone_v3' THEN cl_id END) AS zone_uv
,count(CASE WHEN referrer='feeds' THEN cl_id END) AS feeds_pv
,count(distinct CASE WHEN referrer='feeds' THEN cl_id END) AS feeds_uv
,count(CASE WHEN referrer='recommend' THEN cl_id END) AS recommend_pv
,count(distinct CASE WHEN referrer='recommend' THEN cl_id END) AS recommend_uv
,count(CASE WHEN referrer='content' THEN cl_id END) as content_pv
,count(distinct CASE WHEN referrer='content' THEN cl_id END) as content_uv
,count(CASE WHEN referrer='blank' THEN cl_id END) as blank_pv
,count(distinct CASE WHEN referrer='blank' THEN cl_id END) as blank_uv
,count(CASE WHEN referrer='comment' THEN cl_id END) as comment_pv
,count(distinct CASE WHEN referrer='comment' THEN cl_id END) as comment_uv
,count(CASE WHEN referrer='org' THEN cl_id END) as org_pv
,count(distinct CASE WHEN referrer='org' THEN cl_id END) as org_uv
,count(CASE WHEN referrer='category' THEN cl_id END) as category_pv
,count(distinct CASE WHEN referrer='category' THEN cl_id END) as category_uv
,count(CASE WHEN referrer='my_diary' THEN cl_id END) as my_diary_pv
,count(distinct CASE WHEN referrer='my_diary' THEN cl_id END) as my_diary_uv
,count(CASE WHEN referrer='ai' THEN cl_id END) as ai_pv
,count(distinct CASE WHEN referrer='ai' THEN cl_id END) as ai_uv
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t2.referrer
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
LEFT JOIN
( --不同页面进入内容
SELECT partition_date,cl_id
,case when referrer like 'search_result%' then 'search'
when referrer ='' then 'blank'
when referrer = 'zone_v3' then 'zone_v3'
when referrer='all_case_service_comment' then 'comment'
when referrer in ('organization_detail','expert_detail') then 'org'
when referrer = 'category' then 'category'
when referrer ='my_diary' then 'my_diary'
when referrer in ('face_detect_result','report_result') then 'ai'
when referrer in ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail') then 'content'
else null end as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
and action='page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
UNION ALL
--首页feeds进入内容(首页非策略卡片点击)
SELECT partition_date,cl_id,'feeds' as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'home'
AND action = 'on_click_card'
AND params['transaction_type'] not in ('-1','ctr','cvr','smr','newdata')
AND params['card_content_type'] IN ('diary','diary_topic','user_post','doctor_post','question','answer','qa','live','article')
UNION ALL
--首页feeds进入内容(首页非策略卡片点击) 7.8.0版本前的埋点
SELECT partition_date,cl_id,'feeds' as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'home'
AND action in ( 'on_click_diary_card','on_click_answer_card','on_click_question_card','on_click_topic_card','on_click_live_card')
AND params['transaction_type'] not in ('-1','ctr','cvr','smr','newdata')
UNION ALL
--推荐进入内容(首页策略卡片点击),5月7日新增transaction_type类型
SELECT partition_date,cl_id,'recommend' as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'home'
AND action = 'on_click_card'
AND params['transaction_type'] in ('-1','ctr','cvr','smr','newdata')
AND params['card_content_type'] IN ('diary','diary_topic','user_post','doctor_post','question','answer','qa','live','article')
UNION ALL
--推荐进入内容(首页策略卡片点击) 7.8.0版本前的埋点
SELECT partition_date,cl_id,'feeds' as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'home'
AND action in ('on_click_diary_card','on_click_answer_card','on_click_question_card','on_click_topic_card','on_click_live_card')
AND params['transaction_type'] in ('-1','ctr','cvr','smr','newdata')
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
)t3
LATERAL VIEW explode(t3.channel) t4 AS channel
GROUP BY partition_date,device_os_type,active_type,t4.channel
)T6
ON T1.partition_date=T6.partition_date
AND T1.device_os_type=T6.device_os_type
AND T1.active_type=T6.active_type
AND T1.channel=T6.channel
LEFT JOIN
(--真实发帖数
SELECT partition_date
,device_os_type
,active_type
,t7.channel
,count(distinct id) as num
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t3.id
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
LEFT JOIN
(--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>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.device_id
LEFT JOIN
(--通过user_id,找到发帖情况
--新增帖子
SELECT user_id,id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_api_tractate_view --发帖情况表
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_online='true'
AND platform in ('1','7') --更美用户发的以及打卡的(去除hera后台,爬虫抓取的,kyc自动回复的)
AND regexp_replace(substr(create_time,1,10),'-','')>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND regexp_replace(substr(create_time,1,10),'-','')< regexp_replace((current_date),'-','')
UNION ALL
--新增日记本
SELECT a.user_id,a.id,a.create_date
FROM
(
SELECT user_id,id,regexp_replace(substr(created_time,1,10),'-','') as create_date
FROM online.tl_hdfs_diary_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and regexp_replace(substr(created_time,1,10),'-','') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
and regexp_replace(substr(created_time,1,10),'-','') < regexp_replace((current_date),'-','')
)a
JOIN
( --取非空日记
SELECT diary_id
FROM online.tl_hdfs_problem_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_spam = 'false'
)b
ON a.id = b.diary_id
UNION ALL
--新增日记贴
SELECT user_id,id,regexp_replace(substr(created_time,1,10),'-','') as create_date
FROM online.tl_hdfs_problem_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND regexp_replace(substr(created_time, 1, 10), '-', '') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND regexp_replace(substr(created_time, 1, 10), '-', '') < regexp_replace((current_date),'-','')
AND is_spam = 'false'
AND diary_id is not null
UNION ALL
--新增问题数
SELECT user_id,id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_question_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND regexp_replace(substr(create_time, 1, 10), '-', '') >=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND regexp_replace(substr(create_time, 1, 10), '-', '') < regexp_replace((current_date),'-','')
AND is_spam = 'false'
AND platform= '99' --更美用户发的(去除hera后台,爬虫抓取的,kyc自动回复的)
UNION ALL
--新增回答数
SELECT user_id,id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_answer_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND regexp_replace(substr(create_time, 1, 10), '-', '') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND regexp_replace(substr(create_time, 1, 10), '-', '') < regexp_replace((current_date),'-','')
AND is_spam = 'false'
AND platform= '99' --更美用户发的(去除hera后台,爬虫抓取的,kyc自动回复的)
)t3
ON t2.partition_date = t3.create_date
AND t2.user_id = t3.user_id
JOIN --限制用户是在app进行的发帖
(
SELECT a.partition_date,user_id
FROM
(
SELECT partition_date,user_id,action
FROM online.bl_hdfs_operation_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date< regexp_replace((current_date),'-','')
)a
JOIN
(
SELECT code
FROM dim.dim_community_action_type
WHERE communityuserbehavior_type_name = '发帖'
)type
ON a.action = code
GROUP BY a.partition_date,user_id
)t4
ON t3.user_id = t4.user_id
AND t3.create_date = t4.partition_date
LEFT JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
--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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
) t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_login_doctor = '1'
) t2
ON t1.device_id = t2.device_id
)t5
ON t3.user_id=t5.user_id
where (t5.user_id is null or t5.user_id = '')
)t6
LATERAL VIEW explode(t6.channel) t7 AS channel
GROUP BY partition_date,device_os_type,active_type,t7.channel
)T7
ON T1.partition_date=T7.partition_date
AND T1.device_os_type=T7.device_os_type
AND T1.active_type=T7.active_type
AND T1.channel=T7.channel
LEFT JOIN
(--真实评论数
SELECT partition_date
,device_os_type
,active_type
,t7.channel
,count(distinct id) as num
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t3.id,t3.type
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
LEFT JOIN
(--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>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.device_id
LEFT JOIN
( --有评论过日记帖的设备,排除疑似广告
SELECT t1.user_id,reply_date,t1.id,'topic_reply' as type
FROM
(
SELECT user_id,regexp_replace(substr(reply_date,1,10),'-','') as reply_date,problem_id,id
FROM online.tl_hdfs_topicreply_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_spam = 'false' --排除疑似广告
-- and diary_id is not null 这个表的diary_id有问题,需要join problem表来判断是不是属于日记
and regexp_replace(substr(reply_date,1,10),'-','') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
and regexp_replace(substr(reply_date,1,10),'-','') < regexp_replace((current_date),'-','')
)t1
JOIN
(
SELECT id,diary_id
FROM online.tl_hdfs_problem_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
group by id,diary_id
)t2
on t2.id=t1.problem_id
--group by t1.user_id,reply_date
UNION ALL
--有评论过回答的设备,排除疑似广告
SELECT
t1.user_id,t1.reply_date,t1.id as id,'answer_reply' as type
FROM
(
SELECT user_id,regexp_replace(substr(create_time,1,10),'-','') as reply_date,answer_id,id
FROM online.tl_hdfs_answer_reply_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND (is_fake is NULL or is_fake = 'false')
AND answer_id is not NULL
and regexp_replace(substr(create_time,1,10),'-','') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') < regexp_replace((current_date),'-','')
)t1
JOIN
(
SELECT id,question_id
FROM online.tl_hdfs_answer_view
WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','')
group by id,question_id
)t2
ON t2.id = t1.answer_id
UNION ALL
--有评论过用户帖的设备
SELECT user_id,regexp_replace(substr(create_time,1,10),'-','') as reply_date,id,'tractate_reply' as type
FROM online.tl_hdfs_api_tractate_reply_view
WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') >=regexp_replace(DATE_SUB(current_date,60) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') < regexp_replace((current_date),'-','')
)t3
ON t2.partition_date = t3.reply_date
AND t2.user_id = t3.user_id
JOIN --限制用户是在app进行的回复
(
SELECT a.partition_date,user_id
FROM
(
SELECT partition_date,user_id,action
FROM online.bl_hdfs_operation_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date< regexp_replace((current_date),'-','')
)a
JOIN
(
SELECT code
FROM dim.dim_community_action_type
WHERE communityuserbehavior_type_name = '回帖'
)type
ON a.action = code
GROUP BY a.partition_date,user_id
)t4
ON t3.user_id = t4.user_id
AND t3.reply_date = t4.partition_date
LEFT JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
--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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
) t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_login_doctor = '1'
) t2
ON t1.device_id = t2.device_id
)t5
ON t3.user_id=t5.user_id
where (t5.user_id is null or t5.user_id = '')
)t6
LATERAL VIEW explode(t6.channel) t7 AS channel
GROUP BY partition_date,device_os_type,active_type,t7.channel
)T8
ON T1.partition_date=T8.partition_date
AND T1.device_os_type=T8.device_os_type
AND T1.active_type=T8.active_type
AND T1.channel=T8.channel
LEFT JOIN
(--部分页面的单设备页面浏览时长
SELECT partition_date
,device_os_type
,active_type
,t5.channel
,round(sum(CASE WHEN page_name like 'search%' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS search_stay
,round(sum(CASE WHEN page_name = 'welfare_detail' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS welfare_stay
,round(sum(CASE WHEN page_name = 'question_detail' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS question_stay
,round(sum(CASE WHEN page_name in ('report_result','face_scan','face_detect_result','face_scan_loading','face_institute_report') THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS ai_related_stay
,round(sum(CASE WHEN page_name = 'diary_detail' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS diary_stay
,round(sum(CASE WHEN page_name = 'home' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS home_stay
,round(sum(CASE WHEN page_name in ('conversation_detail','consult_home') THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS conv_stay
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t3.page_name,t3.page_stay
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(--内容用户
SELECT partition_date,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
GROUP BY partition_date,cl_id
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
(--部分页面的停留时长
SELECT partition_date,cl_id,page_name,page_stay
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND (page_name like 'search%' or page_name IN ('welfare_detail','question_detail','report_result','face_scan'
,'face_detect_result','face_scan_loading','face_institute_report','diary_detail','home','conversation_detail','consult_home') )
AND page_name!='search_result'--android埋点会在上报search_result_more时重复上报search_result的埋点,导致page_stay重复计算
AND page_stay>=0 AND page_stay<1000
)t3
ON t2.partition_date=t3.partition_date
AND t2.cl_id=t3.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
)t4
LATERAL VIEW explode(t4.channel) t5 AS channel
GROUP BY partition_date,device_os_type,active_type,t5.channel
)T9
ON T1.partition_date=T9.partition_date
AND T1.device_os_type=T9.device_os_type
AND T1.active_type=T9.active_type
AND T1.channel=T9.channel
ORDER BY day_id desc,device_os_type,active_type,is_ai_channel
"
$hive -e "$sql"
\ No newline at end of file
#!/bin/bash
# 定义变量方便修改
#hive="/opt/spark/spark-2.4.5-bin-hadoop2.7/bin/beeline -u jdbc:hive2://bj-gm-prod-cos-datacenter003:10010 -n data"
hive="/opt/hive/hive-1.1.0-cdh5.16.1/bin/beeline -u jdbc:hive2://bj-gm-prod-cos-datacenter005:10000 -n data"
# 如果是输入的日期按照取输入日期;如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
partition_day=$1
else
partition_day=`date --date="-1 day" +%Y%m%d`
fi
sql="
SET mapreduce.job.queuename=pm;
SET mapreduce.map.memory.mb=8192;
SET mapreduce.map.java.opts=-Xmx8000m;
SET mapreduce.reduce.memory.mb=8192;
SET mapreduce.reduce.java.opts=-Xmx8000m;
set hive.auto.convert.join=true;
SET mapred.reduce.tasks=20;
SET role admin;
ADD JAR hdfs:///user/hive/share/lib/udf/hive-udf-1.0-SNAPSHOT.jar;
CREATE TEMPORARY FUNCTION convup AS 'com.gmei.hive.common.udf.UDFConvUpgrade';
INSERT OVERWRITE TABLE pm.tl_pm_recommend_strategy_d PARTITION (PARTITION_DAY =$partition_day)
SELECT
t1.partition_date as day_id,
t1.device_os_type as device_os_type,
t1.active_type as active_type,
t2.card_content_type as card_content_type,
t2.recommend_type as recommend_type,
NVL(sum(t3.session_pv),0) as card_click,
NVL(sum(t2.session_pv),0) as card_exposure,
NVL(round(sum(page_stay)/count(distinct t4.cl_id)/60,2),0) as avg_page_stay,
NVL(sum(navbar_pv),0) as navbar_search,
NVL(sum(highlight_pv),0) as highlight_word,
NVL(sum(self_wel_pv),0) as self_welfare_card,
NVL(sum(recom_wel_pv),0)-NVL(sum(self_wel_pv),0) as recommend_welfare_card,--需要排除关联的商品卡片点击
NVL(sum(recom_content_pv),0) as recommend_content_card,
NULL as recommend_special_card,
NULL as transfer_card,
NULL as video_consultation
FROM
(
SELECT partition_date
,device_os_type
,CASE WHEN active_type = '4' THEN '老活'
WHEN active_type IN ('1','2') THEN '新增' END AS active_type
,device_id
FROM online.ml_device_day_active_status
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type IN ('1','2','4')
AND first_channel_source_type not IN ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not LIKE 'promotion\_jf\_%'
)t1
JOIN
(--精准曝光,卡片id和session_id去重
SELECT partition_date,
card_content_type,
cl_id,
recommend_type,
card_id,
count(distinct app_session_id) as session_pv
FROM
(
SELECT partition_date,
cl_id,
case when card_content_type in ('qa','answer') then 'qa' else card_content_type end as card_content_type,
CASE WHEN transaction_type in ('ctr') THEN 'ctr预估'
WHEN transaction_type in ('cvr') THEN 'cvr预估'
WHEN transaction_type in ('-1','smr') THEN 'smr'
when transaction_type in ('pgc','hotspot') then '热点卡片'
when transaction_type in ('newdata') then '保量卡片'
END AS recommend_type,
card_id,
app_session_id
from online.ml_community_precise_exposure_detail
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
AND is_exposure = '1' ----精准曝光
AND page_name ='home'
AND tab_name = '精选'
AND transaction_type in ('-1','ctr','smr','cvr','hotspot','pgc','newdata')
AND card_content_type in ('qa','diary','user_post','answer')
group by partition_date,
case when card_content_type in ('qa','answer') then 'qa' else card_content_type end,
cl_id,
CASE WHEN transaction_type in ('ctr') THEN 'ctr预估'
WHEN transaction_type in ('cvr') THEN 'cvr预估'
WHEN transaction_type in ('-1','smr') THEN 'smr'
when transaction_type in ('pgc','hotspot') then '热点卡片'
when transaction_type in ('newdata') then '保量卡片' END,
card_id,
app_session_id
)a
group by partition_date,card_content_type,cl_id,recommend_type,card_id
)t2
on t1.device_id=t2.cl_id and t1.partition_date=t2.partition_date
LEFT JOIN
(--卡片,卡片id和session_id去重
SELECT partition_date,
card_content_type,
cl_id,
recommend_type,
card_id,
count(distinct app_session_id) as session_pv
FROM
(
SELECT partition_date,
cl_id,
case when params['card_content_type'] in ('qa','answer') then 'qa' else params['card_content_type'] end as card_content_type,
CASE WHEN params['transaction_type'] in ('ctr') THEN 'ctr预估'
WHEN params['transaction_type'] in ('cvr') THEN 'cvr预估'
WHEN params['transaction_type'] in ('-1','smr') THEN 'smr'
when params['transaction_type'] in ('pgc','hotspot') then '热点卡片'
when params['transaction_type'] in ('newdata') then '保量卡片'
END AS recommend_type,
params['card_id'] as card_id,
app_session_id
from online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action='on_click_card'
AND params['page_name'] ='home'
AND params['tab_name'] = '精选'
AND params['transaction_type'] in ('-1','ctr','smr','cvr','hotspot','pgc','newdata')
AND params['card_content_type'] in ('qa','diary','user_post','answer')
GROUP BY partition_date,
cl_id,
case when params['card_content_type'] in ('qa','answer') then 'qa' else params['card_content_type'] end,
CASE WHEN params['transaction_type'] in ('ctr') THEN 'ctr预估'
WHEN params['transaction_type'] in ('cvr') THEN 'cvr预估'
WHEN params['transaction_type'] in ('-1','smr') THEN 'smr'
when params['transaction_type'] in ('pgc','hotspot') then '热点卡片'
when params['transaction_type'] in ('newdata') then '保量卡片' END,
params['card_id'],
app_session_id
)a
group by partition_date,card_content_type,cl_id,recommend_type,card_id
)t3
on t2.partition_date=t3.partition_date
and t2.cl_id=t3.cl_id
and t2.card_id=t3.card_id
and t2.card_content_type=t3.card_content_type
and t2.recommend_type=t3.recommend_type
LEFT JOIN
(--页面浏览时长
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
sum(page_stay) as page_stay
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action='page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND referrer='home'
AND page_stay>=0 AND page_stay<1000
GROUP BY partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)t4
on t4.partition_date=t3.partition_date
and t4.cl_id=t3.cl_id
and t4.business_id=t3.card_id
and t4.page_name=t3.card_content_type
LEFT JOIN
(--搜索框和点击行为
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as navbar_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action in ('on_click_navbar_search','do_search')
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)t5
on t5.partition_date=t3.partition_date
and t5.cl_id=t3.cl_id
and t5.business_id=t3.card_id
and t5.page_name=t3.card_content_type
LEFT JOIN
(--点击高亮词
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as highlight_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action='on_click_card'
and params['card_type']='highlight_word'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)t6
on t6.partition_date=t3.partition_date
and t6.cl_id=t3.cl_id
and t6.business_id=t3.card_id
and t6.page_name=t3.card_content_type
LEFT JOIN
(--关联的美购卡片
SELECT partition_date,cl_id,business_id,page_name,count(distinct app_session_id) as self_wel_pv
FROM
(
SELECT partition_date,cl_id,business_id,app_session_id,params['card_id'] as card_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND (get_json_object(params['extra_param'], '$.type')='交互栏'
or get_json_object(params['extra_param'], '$.jump_from')='msg_link'
or params['in_page_pos']='top' or params['in_page_pos']='bottom')
AND action='on_click_card'
and params['card_content_type']='service'
AND page_name IN ('diary_detail','topic_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,app_session_id,params['card_id'],
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)a
group by partition_date,cl_id,business_id,page_name
)t7
on t7.partition_date=t3.partition_date
and t7.cl_id=t3.cl_id
and t7.business_id=t3.card_id
and t7.page_name=t3.card_content_type
LEFT JOIN
(--推荐的美购卡片(需要排除作者消费的美购)
SELECT partition_date,cl_id,business_id,page_name,count(distinct app_session_id) as recom_wel_pv
FROM
(
SELECT partition_date,cl_id,business_id,app_session_id,params['card_id'] as card_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as service_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND (action='on_click_card'and params['card_content_type']='service'
or action='on_click_button' and params['button_name']='unfold')
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,app_session_id,params['card_id'],
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)a
group by partition_date,cl_id,business_id,page_name
)t8
on t8.partition_date=t3.partition_date
and t8.cl_id=t3.cl_id
and t8.business_id=t3.card_id
and t8.page_name=t3.card_content_type
LEFT JOIN
(--推荐的内容卡片
SELECT partition_date,cl_id,business_id,page_name,count(distinct app_session_id) as recom_content_pv
FROM
(
SELECT partition_date,cl_id,business_id,app_session_id,params['card_id'] as card_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as service_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action='on_click_card'
and params['card_content_type'] in ('qa','diary','user_post','answer')
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,app_session_id,params['card_id'],
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)a
group by partition_date,cl_id,business_id,page_name
)t9
on t9.partition_date=t3.partition_date
and t9.cl_id=t3.cl_id
and t9.business_id=t3.card_id
and t9.page_name=t3.card_content_type
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=regexp_replace(DATE_SUB(current_date,1) ,'-','')
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.cl_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>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
)t1
JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
--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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
) t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
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
on t2.partition_date=dev.partition_date and t2.cl_id=dev.device_id
WHERE spam_pv.device_id IS NULL
and dev.device_id is null
GROUP BY t1.partition_date,t1.device_os_type,t1.active_type,t2.card_content_type,t2.recommend_type
order by day_id,device_os_type,active_type,card_content_type,recommend_type;
"
$hive -e "$sql"
\ No newline at end of file
#!/bin/bash
# 定义变量方便修改
#hive="/opt/spark/spark-2.4.5-bin-hadoop2.7/bin/beeline -u jdbc:hive2://bj-gm-prod-cos-datacenter003:10010 -n data"
hive="/opt/hive/hive-1.1.0-cdh5.16.1/bin/beeline -u jdbc:hive2://bj-gm-prod-cos-datacenter005:10000 -n data"
# 如果是输入的日期按照取输入日期;如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
partition_day=$1
else
partition_day=`date --date="-1 day" +%Y%m%d`
fi
sql="
SET mapreduce.job.queuename=data;
SET mapreduce.map.memory.mb=8192;
SET mapreduce.map.java.opts=-Xmx8000m;
SET mapreduce.reduce.memory.mb=8192;
SET mapreduce.reduce.java.opts=-Xmx8000m;
set hive.auto.convert.join=true;
SET mapred.reduce.tasks=20;
SET role admin;
INSERT OVERWRITE TABLE pm.tl_pm_search_click_path_d PARTITION (PARTITION_DAY = $partition_day)
SELECT day_id as day_id
,device_os_type as device_os_type
,active_type as active_type
,v.search_entrance as search_entrance
,sum(search_pv) as click_search_pv
,sum(search_uv) as click_search_uv
FROM
(
SELECT day_id,device_os_type,active_type,array(search_entrance,'合计') as search_entrance
,search_pv,search_uv
FROM
(
SELECT t1.partition_date as day_id
,t1.device_os_type
,t1.active_type
,case when action='on_click_navbar_search' and page_name='home' then '首页搜索框'
when action='on_click_navbar_search' and page_name='welfare_home' then '美购首页搜索框'
when action='on_click_navbar_search' and page_name='category' then '品类聚合页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["home","category"]' then '来自品类聚合的美购列表页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["welfare_home"]' then '来自美购首页的美购列表页搜索框'
when action in ('do_search','on_click_navbar_search')
and page_name in ('diary_detail','topic_detail','post_detail','user_post_detail'
,'doctor_post_detail','question_detail','answer_detail','question_answer_detail') then '内容详情页搜索框'
when action ='详情页高亮词' then '详情页高亮词搜索'
when action='大家都在看' then '首页feed大家都在看'
when action='热搜词' then '美购首页热搜词' else null end as search_entrance
,count(cl_id) as search_pv
,count(distinct cl_id) as search_uv
FROM
(
SELECT partition_date,device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,device_id
FROM online.ml_device_day_active_status
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
join
(
SELECT partition_date,cl_id,page_name,action,params['referrer_link'] as referrer_link
FROM online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and action in ('do_search','on_click_navbar_search')
union all
SELECT partition_date,cl_id,null as page_name,'大家都在看' as action, null as referrer_link
FROM online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND params['in_page_pos']='猜你喜欢'
AND params['tab_name']='精选'
AND params['card_type']='search_word'
--AND page_name='home' android的page_name为空
union all
SELECT partition_date,cl_id,page_name,'热搜词' as action, null as referrer_link
FROM online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND page_name='welfare_home'
AND params['card_type'] ='search_word'
AND params['in_page_pos']='大家都在搜'
union all
select partition_date,cl_id,null as page_name,'详情页高亮词' as action,null as referrer_link
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and action='on_click_card'
and params['card_type']='highlight_word'
)t2
on t1.partition_date=t2.partition_date and t1.device_id=t2.cl_id
group by t1.partition_date
,t1.device_os_type
,t1.active_type
,case when action='on_click_navbar_search' and page_name='home' then '首页搜索框'
when action='on_click_navbar_search' and page_name='welfare_home' then '美购首页搜索框'
when action='on_click_navbar_search' and page_name='category' then '品类聚合页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["home","category"]' then '来自品类聚合的美购列表页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["welfare_home"]' then '来自美购首页的美购列表页搜索框'
when action in ('do_search','on_click_navbar_search')
and page_name in ('diary_detail','topic_detail','post_detail','user_post_detail'
,'doctor_post_detail','question_detail','answer_detail','question_answer_detail') then '内容详情页搜索框'
when action ='详情页高亮词' then '详情页高亮词搜索'
when action='大家都在看' then '首页feed大家都在看'
when action='热搜词' then '美购首页热搜词' else null end
having search_entrance is not null
)t
)n
LATERAL VIEW explode(n.search_entrance) v AS search_entrance
group by day_id,device_os_type,active_type,v.search_entrance;
INSERT OVERWRITE TABLE pm.tl_pm_search_input_type_d PARTITION (PARTITION_DAY = $partition_day)
SELECT partition_date as day_id
,t1.query
,t2.input_type
,sum(t1.all_search_pv) as search_pv
FROM
(
SELECT
partition_date
,query
,array(case when input_type in ('联想','聚合模块') then 'sug点击' else input_type end,'全部') as input_type
,count(click.cl_id) as all_search_pv
,count(distinct click.cl_id) as all_search_uv
FROM
(
SELECT cl_id
,partition_date
,case when params['input_type'] in ('热门','related_search') then '发现' else params['input_type'] end as input_type
,params['query'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action in ('do_search','search_result_click_search')
union all
SELECT cl_id
,partition_date
,'首页精选大家都在看' as input_type
,params['card_name'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND params['in_page_pos']='猜你喜欢'
AND params['tab_name']='精选'
AND params['card_type']='search_word'
--AND page_name='home' android的page_name为空
union all
SELECT cl_id
,partition_date
,'美购首页热搜词' as input_type
,params['card_name'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND page_name='welfare_home'
AND params['card_type'] ='search_word'
AND params['in_page_pos']='大家都在搜'
union all
select cl_id
,partition_date
,'详情页高亮词' as input_type
,params['card_name'] as query
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and int(split(app_version,'\\.')[1]) >= 27
and action='on_click_card'
and params['card_type']='highlight_word'
)click
JOIN
(
SELECT device_id
from online.ml_device_history_detail
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not like 'promotion\_jf\_%'
)dev_channel
on dev_channel.device_id = click.cl_id
GROUP BY partition_date,query,case when input_type in ('联想','聚合模块') then 'sug点击' else input_type end
)t1
LATERAL VIEW explode(t1.input_type) t2 AS input_type
GROUP BY t1.partition_date,t1.query,t2.input_type;
INSERT OVERWRITE TABLE pm.tl_pm_search_result_click_rate_d PARTITION (PARTITION_DAY = $partition_day)
--搜索关键词日报,取近7天数据,每天取关键词搜索量前500
select t1.partition_date as day_id
,t1.query as query
,NVL(t1.search_pv,0) as search_pv
,NVL(t1.search_uv,0) as search_uv
,NVL(t2.search_more_pv,0) as search_more_pv
,NVL(t2.page_more_pv,0) as page_more_pv
,NVL(t2.more_click_pv,0) as more_click_pv
,NVL(t2.more_click_10_pv,0) as more_click_10_pv
,NVL(t2.more_click_5_diary_pv,0) as more_click_5_diary_pv
,NVL(t2.more_click_5_answer_pv,0) as more_click_5_answer_pv
,NVL(t2.more_click_5_topic_pv,0) as more_click_5_topic_pv
,NVL(t2.search_wel_pv,0) as search_wel_pv
,NVL(t2.page_wel_pv,0) as page_wel_pv
,NVL(t2.wel_click_pv,0) as wel_click_pv
,NVL(t2.wel_click_10_pv,0) as wel_click_10_pv
,NVL(t2.wel_click_5_pv,0) as wel_click_5_pv
,NVL(t2.search_diary_pv,0) as search_diary_pv
,NVL(t2.page_diary_pv,0) as page_diary_pv
,NVL(t2.diary_click_pv,0) as diary_click_pv
,NVL(t2.diary_click_10_pv,0) as diary_click_10_pv
,NVL(t2.diary_click_5_pv,0) as diary_click_5_pv
,NVL(t2.search_more_uv,0) as search_more_uv
,NVL(t2.page_more_uv,0) as page_more_uv
,NVL(t2.more_click_uv,0) as more_click_uv
,NVL(t2.more_click_10_uv,0) as more_click_10_uv
,NVL(t2.more_click_5_diary_uv,0) as more_click_5_diary_uv
,NVL(t2.more_click_5_answer_uv,0) as more_click_5_answer_uv
,NVL(t2.more_click_5_topic_uv,0) as more_click_5_topic_uv
,NVL(t2.search_wel_uv,0) as search_wel_uv
,NVL(t2.page_wel_uv,0) as page_wel_uv
,NVL(t2.wel_click_uv,0) as wel_click_uv
,NVL(t2.wel_click_10_uv,0) as wel_click_10_uv
,NVL(t2.wel_click_5_uv,0) as wel_click_5_uv
,NVL(t2.search_diary_uv,0) as search_diary_uv
,NVL(t2.page_diary_uv,0) as page_diary_uv
,NVL(t2.diary_click_uv,0) as diary_click_uv
,NVL(t2.diary_click_10_uv,0) as diary_click_10_uv
,NVL(t2.diary_click_5_uv,0) as diary_click_5_uv
from
(--总搜索量
select partition_date
,query
,search_pv
,search_uv
from
(
select t1.partition_date
,query
,count(t1.cl_id) as search_pv
,count(distinct t1.cl_id) as search_uv
,row_number() over(partition by partition_date order by count(t1.cl_id) desc) as rank
from
(
select partition_date
,params['query'] as query
,cl_id
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and action in ('do_search','search_result_click_search')
union all
SELECT partition_date
,params['card_name'] as query
,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(date_sub(current_date,1),'-','')
AND action = 'on_click_card'
AND params['in_page_pos']='猜你喜欢'
AND params['tab_name']='精选'
AND params['card_type']='search_word'
--AND page_name='home' android的page_name为空
union all
SELECT partition_date
,params['card_name'] as query
,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(date_sub(current_date,1),'-','')
AND action = 'on_click_card'
AND page_name='welfare_home'
AND params['card_type'] ='search_word'
AND params['in_page_pos']='大家都在搜'
union all
select partition_date
,params['card_name'] as query
,cl_id
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and int(split(app_version,'\\.')[1]) >= 27
and action='on_click_card'
and params['card_type']='highlight_word'
)t1
join
(
SELECT device_id
from online.ml_device_history_detail
WHERE partition_date = regexp_replace(date_sub(current_date,1),'-','')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t2
on t1.cl_id=t2.device_id
group by t1.partition_date,query
)t
where rank<=300
)t1
left join
--综合、美购、日记页面浏览pv
(
select t1.partition_date,t1.query
,sum(case when tab_name='综合' then t1.pv end) as search_more_pv
,count(distinct case when tab_name='综合' then t1.cl_id end) as search_more_uv
,sum(case when tab_name='美购' then t1.pv end) as search_wel_pv
,count(distinct case when tab_name='美购' then t1.cl_id end) as search_wel_uv
,sum(case when tab_name='日记' then t1.pv end) as search_diary_pv
,count(distinct case when tab_name='日记' then t1.cl_id end) as search_diary_uv
,sum(case when t2.page_name='综合' then t2.pv end) as page_more_pv
,count(distinct case when t2.page_name='综合' then t2.cl_id end) as page_more_uv
,sum(case when t2.page_name='美购' then t2.pv end) as page_wel_pv
,count(distinct case when t2.page_name='美购' then t2.cl_id end) as page_wel_uv
,sum(case when t2.page_name='日记' then t2.pv end) as page_diary_pv
,count(distinct case when t2.page_name='日记' then t2.cl_id end) as page_diary_uv
,sum(case when t3.page_name='综合' then t3.pv end) as more_click_pv
,count(distinct case when t3.page_name='综合' then t3.cl_id end) as more_click_uv
,sum(case when t3.page_name='美购' then t3.pv end) as wel_click_pv
,count(distinct case when t3.page_name='美购' then t3.cl_id end) as wel_click_uv
,sum(case when t3.page_name='日记' then t3.pv end) as diary_click_pv
,count(distinct case when t3.page_name='日记' then t3.cl_id end) as diary_click_uv
,sum(case when t4.page_name='综合' then t4.pv end) as more_click_10_pv
,count(distinct case when t4.page_name='综合' then t4.cl_id end) as more_click_10_uv
,sum(case when t4.page_name='美购' then t4.pv end) as wel_click_10_pv
,count(distinct case when t4.page_name='美购' then t4.cl_id end) as wel_click_10_uv
,sum(case when t4.page_name='日记' then t4.pv end) as diary_click_10_pv
,count(distinct case when t4.page_name='日记' then t4.cl_id end) as diary_click_10_uv
,sum(case when t5.page_name='美购' then t5.pv end) as wel_click_5_pv
,count(distinct case when t5.page_name='美购' then t5.cl_id end) as wel_click_5_uv
,sum(case when t5.page_name='日记' then t5.pv end) as diary_click_5_pv
,count(distinct case when t5.page_name='日记' then t5.cl_id end) as diary_click_5_uv
,sum(case when t6.page_name='综合' then t6.pv end) as more_click_5_diary_pv
,count(distinct case when t6.page_name='综合' then t6.cl_id end) as more_click_5_diary_uv
,sum(case when t7.page_name='综合' then t7.pv end) as more_click_5_answer_pv
,count(distinct case when t7.page_name='综合' then t7.cl_id end) as more_click_5_answer_uv
,sum(case when t8.page_name='综合' then t8.pv end) as more_click_5_topic_pv
,count(distinct case when t8.page_name='综合' then t8.cl_id end) as more_click_5_topic_uv
from
(--各tab搜索
select partition_date
,params['query'] as query
,cl_id
,params['tab'] as tab_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and params['tab'] in ('综合','美购','日记')
and action in ('search_result_click_tab','search_result_click_search')
group by partition_date,params['query'],cl_id,params['tab']
)t1
left join
(--结果页浏览
select partition_date
,get_json_object(params['extra_param'],'$.query') as query
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end as page_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name in ('search_result_more','search_result_welfare','search_result_diary')
and action ='page_view'
group by partition_date
,get_json_object(params['extra_param'],'$.query')
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end
)t2
on t1.partition_date=t2.partition_date
and t1.query=t2.query
and t1.cl_id=t2.cl_id
and t1.tab_name=t2.page_name
left join
(--内容卡片点击
select partition_date
,params['query'] as query
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end as page_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and action in ('search_result_click_infomation_item','on_click_topic_card','on_click_diary_card','search_result_welfare_click_item')
and page_name in ('search_result_more','search_result_welfare','search_result_diary')
group by partition_date
,params['query']
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end
)t3
on t2.partition_date=t3.partition_date
and t2.query=t3.query
and t2.cl_id=t3.cl_id
and t2.page_name=t3.page_name
left join
(--前10内容卡片点击
select partition_date
,params['query'] as query
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end as page_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and action in ('search_result_click_infomation_item','on_click_topic_card','on_click_diary_card','search_result_welfare_click_item')
and params['position'] in (0,1,2,3,4,5,6,7,8,9)
and page_name in ('search_result_more','search_result_welfare','search_result_diary')
group by partition_date
,params['query']
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end
)t4
on t2.partition_date=t4.partition_date
and t2.query=t4.query
and t2.cl_id=t4.cl_id
and t2.page_name=t4.page_name
left join
(--日记、美购前5内容卡片点击
select partition_date
,params['query'] as query
,cl_id
,case when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end as page_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and ( action = 'on_click_diary_card' and page_name='search_result_diary'
or action ='search_result_welfare_click_item' and page_name='search_result_welfare')
and params['position'] in (0,1,2,3,4)
group by partition_date
,params['query']
,cl_id
,case when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end
)t5
on t2.partition_date=t5.partition_date
and t2.query=t5.query
and t2.cl_id=t5.cl_id
and t2.page_name=t5.page_name
left join
(--综搜页日记卡片前5
select c.partition_date,c.query,c.cl_id,'综合' as page_name,count(1) as pv
from
(
SELECT partition_date,query,position
FROM
(
select partition_date
,params['query'] as query
,cast(absolute_position as int) as position
,row_number() over(partition by params['query'], partition_date order by cast (absolute_position as int) asc) as rank
from online.ml_community_precise_exposure_detail
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
and is_exposure = '1' ----精准曝光
and card_content_type='diary'
group by partition_date,params['query'],cast(absolute_position as int)
)a
where rank<=5
)b
join
(
select partition_date
,params['query'] as query
,cl_id
,params['position'] as position
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and (action ='search_result_click_infomation_item'and params['business_type']in('diary','0')
or action ='on_click_diary_card')
)c
on b.partition_date=c.partition_date
and b.query=c.query
and b.position=c.position
group by c.partition_date,c.query,c.cl_id
)t6
on t2.partition_date=t6.partition_date
and t2.query=t6.query
and t2.cl_id=t6.cl_id
and t2.page_name=t6.page_name
left join
(--综搜页回答卡片前5
select c.partition_date,c.query,c.cl_id,'综合' as page_name,count(1) as pv
from
(
SELECT partition_date,query,position
FROM
(
select partition_date
,params['query'] as query
,cast(absolute_position as int) as position
,row_number() over(partition by params['query'], partition_date order by cast (absolute_position as int) asc) as rank
from online.ml_community_precise_exposure_detail
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
and is_exposure = '1' ----精准曝光
and card_content_type='answer'
group by partition_date,params['query'],cast(absolute_position as int)
)a
where rank<=5
)b
join
(
select partition_date
,params['query'] as query
,cl_id
,params['position'] as position
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and action ='search_result_click_infomation_item'
and params['business_type']in ('answer','5')
)c
on b.partition_date=c.partition_date
and b.query=c.query
and b.position=c.position
group by c.partition_date,c.query,c.cl_id
)t7
on t2.partition_date=t7.partition_date
and t2.query=t7.query
and t2.cl_id=t7.cl_id
and t2.page_name=t7.page_name
left join
(--综搜页帖子卡片前5
select c.partition_date,c.query,c.cl_id,'综合' as page_name,count(1) as pv
from
(
SELECT partition_date,query,position
FROM
(
select partition_date
,params['query'] as query
,cast(absolute_position as int) as position
,row_number() over(partition by params['query'], partition_date order by cast (absolute_position as int) asc) as rank
from online.ml_community_precise_exposure_detail
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
and is_exposure = '1' ----精准曝光
and card_content_type='user_post'
group by partition_date,params['query'],cast(absolute_position as int)
)a
where rank<=5
)b
join
(
select partition_date
,params['query'] as query
,cl_id
,params['position'] as position
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and (action ='search_result_click_infomation_item' and params['business_type'] in ('post','user_post','doctor_post','11')
or action='on_click_topic_card')
)c
on b.partition_date=c.partition_date
and b.query=c.query
and b.position=c.position
group by c.partition_date,c.query,c.cl_id
)t8
on t2.partition_date=t8.partition_date
and t2.query=t8.query
and t2.cl_id=t8.cl_id
and t2.page_name=t8.page_name
join
(
select device_id
from online.ml_device_history_detail
WHERE partition_date = regexp_replace(date_sub(current_date,1),'-','')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not like 'promotion\_jf\_%'
)dev
on t1.cl_id=dev.device_id
left join
( -- 去掉疑似机构刷量的PV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(date_sub(current_date,1),'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
group by t1.partition_date,t1.query
)t2
on t1.partition_date=t2.partition_date
and t1.query=t2.query
order by day_id desc,search_pv desc,query;
"
$hive -e "$sql"
\ No newline at end of file
--内容日报
SELECT
day_id AS `日期`
,device_os_type AS `设备类型`
,active_type AS `活跃类型`
,is_ai_channel AS `是否AI渠道`
,dau AS `DAU`
,content_uv AS `内容详情页UV`
,content_pv AS `内容详情页PV`
,per_content_uv AS `内容UV/DAU`
,per_content_pv AS `内容PV/内容UV`
,retention_1 AS `内容用户APP次留`
,retention_7 AS `内容用户APP7留`
,retention_30 AS `内容用户APP30留`
,avg_app_duration AS `内容用户单设备App时长(m)`
,avg_content_stay AS `内容用户单设备内容时长(m)`
,avg_open_times AS `内容用户单设备打开次数`
,search_related_stay AS `内容用户搜索相关页面单设备页面时长(m)`
,welfare_stay AS `内容用户美购详情页单设备页面时长(m)`
,content_question_stay AS `内容用户问题详情页单设备页面时长(m)`
,ai_related_stay AS `内容用户AI相关页面单设备页面时长(m)`
,content_diary_stay AS `内容用户日记详情页单设备页面时长(m)`
,home_stay AS `内容用户首页单设备页面时长(m)`
,conv_related_stay AS `内容用户咨询相关页面单设备页面时长(m)`
,recommend_rate AS `首页feeds推荐进入内容UV/内容UV`
,per_recommend_pv AS `首页feeds推荐进入内容PV/UV`
,feeds_rate AS `首页feeds非推荐进入内容UV/内容UV`
,per_feeds_pv AS `首页feeds非推荐进入内容PV/UV`
,search_rate AS `搜索进入内容UV/内容UV`
,per_search_pv AS `搜索进入内容PV/UV`
,zone_rate AS `内容聚合页进入内容UV/内容UV`
,per_zone_pv AS `内容聚合页进入内容PV/UV`
,content_rate AS `内容详情页推荐板块进入内容UV/内容UV`
,per_from_content_pv AS `内容详情页推荐板块进入内容PV/UV`
,blank_rate AS `无来源页面(大多数为push)进入内容UV/内容UV`
,per_blank_pv AS `无来源页面(大多数为push)进入内容PV/UV`
,comment_rate AS `评论列表页进入内容UV/内容UV`
,per_comment_pv AS `评论列表页进入内容PV/UV`
,org_rate AS `医生医院主页进入内容UV/内容UV`
,per_org_pv AS `医生医院主页进入内容PV/UV`
,category_rate AS `品类聚合页进入内容UV/内容UV`
,per_category_pv AS `品类聚合页进入内容PV/UV`
,my_diary_rate AS `我的日记页进入内容UV/内容UV`
,per_my_diary_pv AS `我的日记页进入内容PV/UV`
,ai_rate AS `AI报告页进入内容UV/内容UV`
,per_ai_pv AS `AI报告页进入内容PV/UV`
,diary_uv AS `日记UV`
,diary_pv AS `日记PV`
,diary_rate AS `日记UV/内容UV`
,per_diary_pv AS `日记PV/日记UV`
,diary_stay AS `日记单设备时长(m)`
,post_uv AS `帖子UV`
,post_pv AS `帖子PV`
,post_rate AS `帖子UV/内容UV`
,per_post_pv AS `帖子PV/帖子UV`
,post_stay AS `帖子单设备时长(m)`
,question_uv AS `问题UV`
,question_pv AS `问题PV`
,question_rate AS `问题UV/内容UV`
,per_question_pv AS `问题PV/问题UV`
,question_stay AS `问题单设备时长(m)`
,question_answer_uv AS `问答UV`
,question_answer_pv AS `问答PV`
,question_answer_rate AS `问答UV/内容UV`
,per_question_answer_pv AS `问答PV/问答UV`
,question_answer_stay AS `问答单设备时长(m)`
,answer_uv AS `回答UV`
,answer_pv AS `回答PV`
,answer_rate AS `回答UV/内容UV`
,per_answer_pv AS `回答PV/回答UV`
,answer_stay AS `回答单设备时长(m)`
,video_uv AS `视频UV`
,video_pv AS `视频PV`
,video_rate AS `视频UV/内容UV`
,per_video_pv AS `视频PV/视频UV`
,video_stay AS `视频单设备时长(m)`
,wiki_uv AS `百科UV`
,wiki_pv AS `百科PV`
,wiki_rate AS `百科UV/内容UV`
,per_wiki_pv AS `百科PV/百科UV`
,wiki_stay AS `百科单设备时长(m)`
,article_uv AS `专栏UV`
,article_pv AS `专栏PV`
,article_rate AS `专栏UV/内容UV`
,per_article_pv AS `专栏PV/专栏UV`
,article_stay AS `专栏单设备时长(m)`
FROM pm.tl_pm_content_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
INSERT OVERWRITE TABLE pm.tl_pm_content_d PARTITION (PARTITION_DAY = ${partition_day})
SELECT
T1.partition_date AS day_id
,T1.device_os_type AS device_os_type
,T1.active_type AS active_type
,T1.channel AS is_ai_channel
,COALESCE(T1.dau,0) AS dau
,COALESCE(T2.neirong_uv,0) AS content_uv
,COALESCE(T2.neirong_pv,0) AS content_pv
,COALESCE(ROUND(T2.neirong_uv/T1.dau,2),0) AS per_content_uv
,COALESCE(ROUND(T2.neirong_pv/T2.neirong_uv,2),0) AS per_content_pv
,COALESCE(CONCAT(ROUND(T4.retention_num1/T2.neirong_uv*100,2),'%'),0) AS retention_1
,COALESCE(CONCAT(ROUND(T4.retention_num7/T2.neirong_uv*100,2),'%'),0) AS retention_7
,COALESCE(CONCAT(ROUND(T4.retention_num30/T2.neirong_uv*100,2),'%'),0) AS retention_30
,COALESCE(T5.app_duration,0) AS avg_app_duration
,COALESCE(T3.neirong_stay,0) AS avg_content_stay
,COALESCE(T5.avg_opentimes,0) AS avg_open_times
,COALESCE(T9.search_stay,0) AS search_related_stay
,COALESCE(T9.welfare_stay,0) AS welfare_stay
,COALESCE(T9.question_stay,0) AS content_question_stay
,COALESCE(T9.ai_related_stay,0) AS ai_related_stay
,COALESCE(T9.diary_stay,0) AS content_diary_stay
,COALESCE(T9.home_stay,0) AS home_stay
,COALESCE(T9.conv_stay,0) AS conv_related_stay
,COALESCE(ROUND(T6.recommend_uv/T2.neirong_uv,2),0) AS recommend_rate
,COALESCE(ROUND(T6.recommend_pv/T6.recommend_uv,2),0) AS per_recommend_pv
,COALESCE(ROUND(T6.feeds_uv/T2.neirong_uv,2),0) AS feeds_rate
,COALESCE(ROUND(T6.feeds_pv/T6.feeds_uv,2),0) AS per_feeds_pv
,COALESCE(ROUND(T6.search_uv/T2.neirong_uv,2),0) AS search_rate
,COALESCE(ROUND(T6.search_pv/T6.search_uv,2),0) AS per_search_pv
,COALESCE(ROUND(T6.zone_uv/T2.neirong_uv,2),0) AS zone_rate
,COALESCE(ROUND(T6.zone_pv/T6.zone_uv,2),0) AS per_zone_pv
,COALESCE(ROUND(T6.content_uv/T2.neirong_uv,2),0) AS content_rate
,COALESCE(ROUND(T6.content_pv/T6.content_uv,2),0) AS per_from_content_pv
,COALESCE(ROUND(T6.blank_uv/T2.neirong_uv,2),0) AS blank_rate
,COALESCE(ROUND(T6.blank_pv/T6.blank_uv,2),0) AS per_blank_pv
,COALESCE(ROUND(T6.comment_uv/T2.neirong_uv,2),0) AS comment_rate
,COALESCE(ROUND(T6.comment_pv/T6.comment_uv,2),0) AS per_comment_pv
,COALESCE(ROUND(T6.org_uv/T2.neirong_uv,2),0) AS org_rate
,COALESCE(ROUND(T6.org_pv/T6.org_uv,2),0) AS per_org_pv
,COALESCE(ROUND(T6.category_uv/T2.neirong_uv,2),0) AS category_rate
,COALESCE(ROUND(T6.category_pv/T6.category_uv,2),0) AS per_category_pv
,COALESCE(ROUND(T6.my_diary_uv/T2.neirong_uv,2),0) AS my_diary_rate
,COALESCE(ROUND(T6.my_diary_pv/T6.my_diary_uv,2),0) AS per_my_diary_pv
,COALESCE(ROUND(T6.ai_uv/T2.neirong_uv,2),0) AS ai_rate
,COALESCE(ROUND(T6.ai_pv/T6.ai_uv,2),0) AS per_ai_pv
,null AS create_topic_num
,null AS create_reply_num
,COALESCE(T2.diary_uv,0) AS diary_uv
,COALESCE(T2.diary_pv,0) AS diary_pv
,COALESCE(ROUND(T2.diary_uv/T2.neirong_uv,2),0) AS diary_rate
,COALESCE(ROUND(T2.diary_pv/T2.diary_uv,2),0) AS per_diary_pv
,COALESCE(T3.diary_stay,0) AS diary_stay
,COALESCE(T2.post_uv,0) AS post_uv
,COALESCE(T2.post_pv,0) AS post_pv
,COALESCE(ROUND(T2.post_uv/T2.neirong_uv,2),0) AS post_rate
,COALESCE(ROUND(T2.post_pv/T2.post_uv,2),0) AS per_post_pv
,COALESCE(T3.post_stay,0) AS post_stay
,COALESCE(T2.question_uv,0) AS question_uv
,COALESCE(T2.question_pv,0) AS question_pv
,COALESCE(ROUND(T2.question_uv/T2.neirong_uv,2),0) AS question_rate
,COALESCE(ROUND(T2.question_pv/T2.question_uv,2),0) AS per_question_pv
,COALESCE(T3.question_stay,0) AS question_stay
,COALESCE(T2.question_answer_uv,0) AS question_answer_uv
,COALESCE(T2.question_answer_pv,0) AS question_answer_pv
,COALESCE(ROUND(T2.question_answer_uv/T2.neirong_uv,2),0) AS question_answer_rate
,COALESCE(ROUND(T2.question_answer_pv/T2.question_answer_uv,2),0) AS per_question_answer_pv
,COALESCE(T3.question_answer_stay,0) AS question_answer_stay
,COALESCE(T2.answer_uv,0) AS answer_uv
,COALESCE(T2.answer_pv,0) AS answer_pv
,COALESCE(ROUND(T2.answer_uv/T2.neirong_uv,2),0) AS answer_rate
,COALESCE(ROUND(T2.answer_pv/T2.answer_uv,2),0) AS per_answer_pv
,COALESCE(T3.answer_stay,0) AS answer_stay
,COALESCE(T2.video_uv,0) AS video_uv
,COALESCE(T2.video_pv,0) AS video_pv
,COALESCE(ROUND(T2.video_uv/T2.neirong_uv,2),0) AS video_rate
,COALESCE(ROUND(T2.video_pv/T2.video_uv,2),0) AS per_video_pv
,COALESCE(T3.video_stay,0) AS video_stay
,COALESCE(T2.wiki_uv,0) AS wiki_uv
,COALESCE(T2.wiki_pv,0) AS wiki_pv
,COALESCE(ROUND(T2.wiki_uv/T2.neirong_uv,2),0) AS wiki_rate
,COALESCE(ROUND(T2.wiki_pv/T2.wiki_uv,2),0) AS per_wiki_pv
,COALESCE(T3.wiki_stay,0) AS wiki_stay
,COALESCE(T2.article_uv,0) AS article_uv
,COALESCE(T2.article_pv,0) AS article_pv
,COALESCE(ROUND(T2.article_uv/T2.neirong_uv,2),0) AS article_rate
,COALESCE(ROUND(T2.article_pv/T2.article_uv,2),0) AS per_article_pv
,COALESCE(T3.article_stay,0) AS article_stay
FROM
(--基础维度/dau
SELECT partition_date,device_os_type,active_type,t2.channel,count(distinct device_id) AS dau
FROM
(
SELECT partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY partition_date,device_os_type,active_type,t2.channel
)T1
LEFT JOIN
(--内容uv/pv
SELECT partition_date
,device_os_type
,active_type
,t4.channel
,count(cl_id) as neirong_pv
,count(distinct cl_id) as neirong_uv
,count(CASE WHEN page_name IN ('diary_detail','topic_detail') THEN cl_id END) AS diary_pv
,count(distinct CASE WHEN page_name IN ('diary_detail','topic_detail') THEN cl_id END) AS diary_uv
,count(CASE WHEN page_name IN ('post_detail','user_post_detail','doctor_post_detail') THEN cl_id END) AS post_pv
,count(distinct CASE WHEN page_name IN ('post_detail','user_post_detail','doctor_post_detail') THEN cl_id END) AS post_uv
,count(CASE WHEN page_name ='question_detail' THEN cl_id END) AS question_pv
,count(distinct CASE WHEN page_name ='question_detail' THEN cl_id END) AS question_uv
,count(CASE WHEN page_name ='question_answer_detail' THEN cl_id END) AS question_answer_pv
,count(distinct CASE WHEN page_name ='question_answer_detail' THEN cl_id END) AS question_answer_uv
,count(CASE WHEN page_name='answer_detail' THEN cl_id END) AS answer_pv
,count(distinct CASE WHEN page_name='answer_detail' THEN cl_id END) AS answer_uv
,count(CASE WHEN page_name='video_steep' THEN cl_id END) AS video_pv
,count(distinct CASE WHEN page_name='video_steep' THEN cl_id END) AS video_uv
,count(CASE WHEN page_name='article_detail' THEN cl_id END) AS article_pv
,count(distinct CASE WHEN page_name='article_detail' THEN cl_id END) AS article_uv
,count(CASE WHEN page_name IN ('wiki_detail','product_detail','wiki_brand','wiki_collect') THEN cl_id END) AS wiki_pv
,count(distinct CASE WHEN page_name IN ('wiki_detail','product_detail','wiki_brand','wiki_collect') THEN cl_id END) AS wiki_uv
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t2.page_name
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(
SELECT partition_date,page_name,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
)t3
LATERAL VIEW explode(t3.channel) t4 AS channel
GROUP BY partition_date,device_os_type,active_type,t4.channel
)T2
ON T1.partition_date=T2.partition_date
AND T1.device_os_type=T2.device_os_type
AND T1.active_type=T2.active_type
AND T1.channel=T2.channel
LEFT JOIN
(--内容浏览时长
SELECT partition_date
,device_os_type
,active_type
,t4.channel
,round(sum(page_stay)/count(distinct cl_id)/60,4) as neirong_stay
,round(sum(CASE WHEN page_name IN ('diary_detail','topic_detail') THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name IN ('diary_detail','topic_detail') THEN cl_id END)/60,4) AS diary_stay
,round(sum(CASE WHEN page_name IN ('post_detail','user_post_detail','doctor_post_detail') THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name IN ('post_detail','user_post_detail','doctor_post_detail') THEN cl_id END)/60,4) AS post_stay
,round(sum(CASE WHEN page_name ='question_detail' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='question_detail' THEN cl_id END)/60,4) AS question_stay
,round(sum(CASE WHEN page_name ='question_answer_detail' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='question_answer_detail' THEN cl_id END)/60,4) AS question_answer_stay
,round(sum(CASE WHEN page_name ='answer_detail' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='answer_detail' THEN cl_id END)/60,4) AS answer_stay
,round(sum(CASE WHEN page_name ='video_steep' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='video_steep' THEN cl_id END)/60,4) AS video_stay
,round(sum(CASE WHEN page_name ='article_detail' THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name ='article_detail' THEN cl_id END)/60,4) AS article_stay
,round(sum(CASE WHEN page_name IN ('wiki_detail','product_detail','wiki_brand','wiki_collect') THEN page_stay else 0 END)/
count(distinct CASE WHEN page_name IN ('wiki_detail','product_detail','wiki_brand','wiki_collect') THEN cl_id END)/60,4) AS wiki_stay
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t2.page_name,t2.page_stay
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(
SELECT partition_date,page_name,cl_id,page_stay
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
AND page_stay>=0 AND page_stay<1000
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
)t3
LATERAL VIEW explode(t3.channel) t4 AS channel
GROUP BY partition_date,device_os_type,active_type,t4.channel
)T3
ON T1.partition_date=T3.partition_date
AND T1.device_os_type=T3.device_os_type
AND T1.active_type=T3.active_type
AND T1.channel=T3.channel
LEFT JOIN
(--内容用户留存
SELECT regexp_replace(partition_date,'-','') AS partition_date
,device_os_type,active_type,t5.channel
,int(count(DISTINCT CASE WHEN date_add(partition_date,1) = retention_date THEN device_id END)) AS retention_num1
,int(count(DISTINCT CASE WHEN date_add(partition_date,6) = retention_date THEN device_id END)) AS retention_num7
,int(count(DISTINCT CASE WHEN date_add(partition_date,29) = retention_date THEN device_id END)) AS retention_num30
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t3.device_id,t3.partition_date as retention_date
FROM
(
SELECT
concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(--内容用户
SELECT cl_id
,concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) AS partition_date
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
GROUP BY cl_id,concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2))
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
LEFT JOIN
(--活跃设备
SELECT device_id
,concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) AS partition_date
FROM online.ml_device_day_active_status
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
)t3
ON t2.cl_id=t3.device_id
WHERE spam_pv.device_id IS NULL
)t4
LATERAL VIEW explode(t4.channel) t5 AS channel
GROUP BY regexp_replace(partition_date,'-',''),device_os_type,active_type,t5.channel
)T4
ON T1.partition_date=T4.partition_date
AND T1.device_os_type=T4.device_os_type
AND T1.active_type=T4.active_type
AND T1.channel=T4.channel
LEFT JOIN
(--内容用户单设备app时长(m)
SELECT partition_date
,device_os_type
,active_type
,t5.channel
,round(sum(use_duration)/count(distinct cl_id)/60,4) as app_duration
,round(avg(open_times),4) as avg_opentimes
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t3.use_duration,t3.open_times
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(--内容用户
SELECT partition_date,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
GROUP BY partition_date,cl_id
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
LEFT JOIN
(
SELECT partition_date,device_id,use_duration,open_times
FROM online.ml_device_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND use_duration > 0 and use_duration < 86400
)t3
on t2.partition_date=t3.partition_date
AND t2.cl_id=t3.device_id
WHERE spam_pv.device_id IS NULL
)t4
LATERAL VIEW explode(t4.channel) t5 AS channel
GROUP BY partition_date,device_os_type,active_type,t5.channel
)T5
ON T1.partition_date=T5.partition_date
AND T1.device_os_type=T5.device_os_type
AND T1.active_type=T5.active_type
AND T1.channel=T5.channel
LEFT JOIN
(--不同来源进入内容uv/pv
SELECT partition_date
,device_os_type
,active_type
,t4.channel
,count(CASE WHEN referrer='search' THEN cl_id END) AS search_pv
,count(distinct CASE WHEN referrer='search' THEN cl_id END) AS search_uv
,count(CASE WHEN referrer='zone_v3' THEN cl_id END) AS zone_pv
,count(distinct CASE WHEN referrer='zone_v3' THEN cl_id END) AS zone_uv
,count(CASE WHEN referrer='feeds' THEN cl_id END) AS feeds_pv
,count(distinct CASE WHEN referrer='feeds' THEN cl_id END) AS feeds_uv
,count(CASE WHEN referrer='recommend' THEN cl_id END) AS recommend_pv
,count(distinct CASE WHEN referrer='recommend' THEN cl_id END) AS recommend_uv
,count(CASE WHEN referrer='content' THEN cl_id END) as content_pv
,count(distinct CASE WHEN referrer='content' THEN cl_id END) as content_uv
,count(CASE WHEN referrer='blank' THEN cl_id END) as blank_pv
,count(distinct CASE WHEN referrer='blank' THEN cl_id END) as blank_uv
,count(CASE WHEN referrer='comment' THEN cl_id END) as comment_pv
,count(distinct CASE WHEN referrer='comment' THEN cl_id END) as comment_uv
,count(CASE WHEN referrer='org' THEN cl_id END) as org_pv
,count(distinct CASE WHEN referrer='org' THEN cl_id END) as org_uv
,count(CASE WHEN referrer='category' THEN cl_id END) as category_pv
,count(distinct CASE WHEN referrer='category' THEN cl_id END) as category_uv
,count(CASE WHEN referrer='my_diary' THEN cl_id END) as my_diary_pv
,count(distinct CASE WHEN referrer='my_diary' THEN cl_id END) as my_diary_uv
,count(CASE WHEN referrer='ai' THEN cl_id END) as ai_pv
,count(distinct CASE WHEN referrer='ai' THEN cl_id END) as ai_uv
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t2.referrer
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
LEFT JOIN
( --不同页面进入内容
SELECT partition_date,cl_id
,case when referrer like 'search_result%' then 'search'
when referrer ='' then 'blank'
when referrer = 'zone_v3' then 'zone_v3'
when referrer='all_case_service_comment' then 'comment'
when referrer in ('organization_detail','expert_detail') then 'org'
when referrer = 'category' then 'category'
when referrer ='my_diary' then 'my_diary'
when referrer in ('face_detect_result','report_result') then 'ai'
when referrer in ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail') then 'content'
else null end as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
and action='page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
UNION ALL
--首页feeds进入内容(首页非策略卡片点击)
SELECT partition_date,cl_id,'feeds' as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'home'
AND action = 'on_click_card'
AND params['transaction_type'] not in ('-1','ctr','cvr','smr','newdata')
AND params['card_content_type'] IN ('diary','diary_topic','user_post','doctor_post','question','answer','qa','live','article')
UNION ALL
--首页feeds进入内容(首页非策略卡片点击) 7.8.0版本前的埋点
SELECT partition_date,cl_id,'feeds' as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'home'
AND action in ( 'on_click_diary_card','on_click_answer_card','on_click_question_card','on_click_topic_card','on_click_live_card')
AND params['transaction_type'] not in ('-1','ctr','cvr','smr','newdata')
UNION ALL
--推荐进入内容(首页策略卡片点击),5月7日新增transaction_type类型
SELECT partition_date,cl_id,'recommend' as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'home'
AND action = 'on_click_card'
AND params['transaction_type'] in ('-1','ctr','cvr','smr','newdata')
AND params['card_content_type'] IN ('diary','diary_topic','user_post','doctor_post','question','answer','qa','live','article')
UNION ALL
--推荐进入内容(首页策略卡片点击) 7.8.0版本前的埋点
SELECT partition_date,cl_id,'feeds' as referrer
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'home'
AND action in ('on_click_diary_card','on_click_answer_card','on_click_question_card','on_click_topic_card','on_click_live_card')
AND params['transaction_type'] in ('-1','ctr','cvr','smr','newdata')
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
)t3
LATERAL VIEW explode(t3.channel) t4 AS channel
GROUP BY partition_date,device_os_type,active_type,t4.channel
)T6
ON T1.partition_date=T6.partition_date
AND T1.device_os_type=T6.device_os_type
AND T1.active_type=T6.active_type
AND T1.channel=T6.channel
LEFT JOIN
(--真实发帖数
SELECT partition_date
,device_os_type
,active_type
,t7.channel
,count(distinct id) as num
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t3.id
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
LEFT JOIN
(--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>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.device_id
LEFT JOIN
(--通过user_id,找到发帖情况
--新增帖子
SELECT user_id,id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_api_tractate_view --发帖情况表
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_online='true'
AND platform in ('1','7') --更美用户发的以及打卡的(去除hera后台,爬虫抓取的,kyc自动回复的)
AND regexp_replace(substr(create_time,1,10),'-','')>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND regexp_replace(substr(create_time,1,10),'-','')< regexp_replace((current_date),'-','')
UNION ALL
--新增日记本
SELECT a.user_id,a.id,a.create_date
FROM
(
SELECT user_id,id,regexp_replace(substr(created_time,1,10),'-','') as create_date
FROM online.tl_hdfs_diary_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and regexp_replace(substr(created_time,1,10),'-','') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
and regexp_replace(substr(created_time,1,10),'-','') < regexp_replace((current_date),'-','')
)a
JOIN
( --取非空日记
SELECT diary_id
FROM online.tl_hdfs_problem_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_spam = 'false'
)b
ON a.id = b.diary_id
UNION ALL
--新增日记贴
SELECT user_id,id,regexp_replace(substr(created_time,1,10),'-','') as create_date
FROM online.tl_hdfs_problem_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND regexp_replace(substr(created_time, 1, 10), '-', '') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND regexp_replace(substr(created_time, 1, 10), '-', '') < regexp_replace((current_date),'-','')
AND is_spam = 'false'
AND diary_id is not null
UNION ALL
--新增问题数
SELECT user_id,id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_question_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND regexp_replace(substr(create_time, 1, 10), '-', '') >=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND regexp_replace(substr(create_time, 1, 10), '-', '') < regexp_replace((current_date),'-','')
AND is_spam = 'false'
AND platform= '99' --更美用户发的(去除hera后台,爬虫抓取的,kyc自动回复的)
UNION ALL
--新增回答数
SELECT user_id,id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_answer_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND regexp_replace(substr(create_time, 1, 10), '-', '') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND regexp_replace(substr(create_time, 1, 10), '-', '') < regexp_replace((current_date),'-','')
AND is_spam = 'false'
AND platform= '99' --更美用户发的(去除hera后台,爬虫抓取的,kyc自动回复的)
)t3
ON t2.partition_date = t3.create_date
AND t2.user_id = t3.user_id
JOIN --限制用户是在app进行的发帖
(
SELECT a.partition_date,user_id
FROM
(
SELECT partition_date,user_id,action
FROM online.bl_hdfs_operation_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date< regexp_replace((current_date),'-','')
)a
JOIN
(
SELECT code
FROM dim.dim_community_action_type
WHERE communityuserbehavior_type_name = '发帖'
)type
ON a.action = code
GROUP BY a.partition_date,user_id
)t4
ON t3.user_id = t4.user_id
AND t3.create_date = t4.partition_date
LEFT JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
--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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
) t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_login_doctor = '1'
) t2
ON t1.device_id = t2.device_id
)t5
ON t3.user_id=t5.user_id
where (t5.user_id is null or t5.user_id = '')
)t6
LATERAL VIEW explode(t6.channel) t7 AS channel
GROUP BY partition_date,device_os_type,active_type,t7.channel
)T7
ON T1.partition_date=T7.partition_date
AND T1.device_os_type=T7.device_os_type
AND T1.active_type=T7.active_type
AND T1.channel=T7.channel
LEFT JOIN
(--真实评论数
SELECT partition_date
,device_os_type
,active_type
,t7.channel
,count(distinct id) as num
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t3.id,t3.type
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
LEFT JOIN
(--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>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.device_id
LEFT JOIN
( --有评论过日记帖的设备,排除疑似广告
SELECT t1.user_id,reply_date,t1.id,'topic_reply' as type
FROM
(
SELECT user_id,regexp_replace(substr(reply_date,1,10),'-','') as reply_date,problem_id,id
FROM online.tl_hdfs_topicreply_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_spam = 'false' --排除疑似广告
-- and diary_id is not null 这个表的diary_id有问题,需要join problem表来判断是不是属于日记
and regexp_replace(substr(reply_date,1,10),'-','') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
and regexp_replace(substr(reply_date,1,10),'-','') < regexp_replace((current_date),'-','')
)t1
JOIN
(
SELECT id,diary_id
FROM online.tl_hdfs_problem_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
group by id,diary_id
)t2
on t2.id=t1.problem_id
--group by t1.user_id,reply_date
UNION ALL
--有评论过回答的设备,排除疑似广告
SELECT
t1.user_id,t1.reply_date,t1.id as id,'answer_reply' as type
FROM
(
SELECT user_id,regexp_replace(substr(create_time,1,10),'-','') as reply_date,answer_id,id
FROM online.tl_hdfs_answer_reply_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND (is_fake is NULL or is_fake = 'false')
AND answer_id is not NULL
and regexp_replace(substr(create_time,1,10),'-','') >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') < regexp_replace((current_date),'-','')
)t1
JOIN
(
SELECT id,question_id
FROM online.tl_hdfs_answer_view
WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','')
group by id,question_id
)t2
ON t2.id = t1.answer_id
UNION ALL
--有评论过用户帖的设备
SELECT user_id,regexp_replace(substr(create_time,1,10),'-','') as reply_date,id,'tractate_reply' as type
FROM online.tl_hdfs_api_tractate_reply_view
WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') >=regexp_replace(DATE_SUB(current_date,60) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') < regexp_replace((current_date),'-','')
)t3
ON t2.partition_date = t3.reply_date
AND t2.user_id = t3.user_id
JOIN --限制用户是在app进行的回复
(
SELECT a.partition_date,user_id
FROM
(
SELECT partition_date,user_id,action
FROM online.bl_hdfs_operation_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date< regexp_replace((current_date),'-','')
)a
JOIN
(
SELECT code
FROM dim.dim_community_action_type
WHERE communityuserbehavior_type_name = '回帖'
)type
ON a.action = code
GROUP BY a.partition_date,user_id
)t4
ON t3.user_id = t4.user_id
AND t3.reply_date = t4.partition_date
LEFT JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
--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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
) t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_login_doctor = '1'
) t2
ON t1.device_id = t2.device_id
)t5
ON t3.user_id=t5.user_id
where (t5.user_id is null or t5.user_id = '')
)t6
LATERAL VIEW explode(t6.channel) t7 AS channel
GROUP BY partition_date,device_os_type,active_type,t7.channel
)T8
ON T1.partition_date=T8.partition_date
AND T1.device_os_type=T8.device_os_type
AND T1.active_type=T8.active_type
AND T1.channel=T8.channel
LEFT JOIN
(--部分页面的单设备页面浏览时长
SELECT partition_date
,device_os_type
,active_type
,t5.channel
,round(sum(CASE WHEN page_name like 'search%' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS search_stay
,round(sum(CASE WHEN page_name = 'welfare_detail' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS welfare_stay
,round(sum(CASE WHEN page_name = 'question_detail' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS question_stay
,round(sum(CASE WHEN page_name in ('report_result','face_scan','face_detect_result','face_scan_loading','face_institute_report') THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS ai_related_stay
,round(sum(CASE WHEN page_name = 'diary_detail' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS diary_stay
,round(sum(CASE WHEN page_name = 'home' THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS home_stay
,round(sum(CASE WHEN page_name in ('conversation_detail','consult_home') THEN page_stay else 0 END)/count(distinct cl_id)/60,4) AS conv_stay
FROM
(
SELECT t1.partition_date,device_os_type,active_type,channel,t2.cl_id,t3.page_name,t3.page_stay
FROM
(
SELECT
partition_date
,m.device_id, device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20200101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date>=regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
JOIN
(--内容用户
SELECT partition_date,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail','wiki_detail','product_detail','wiki_brand','wiki_collect')
GROUP BY partition_date,cl_id
)t2
ON t1.partition_date=t2.partition_date
AND t1.device_id=t2.cl_id
LEFT JOIN
(--部分页面的停留时长
SELECT partition_date,cl_id,page_name,page_stay
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,60) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND action = 'page_view'
AND (page_name like 'search%' or page_name IN ('welfare_detail','question_detail','report_result','face_scan'
,'face_detect_result','face_scan_loading','face_institute_report','diary_detail','home','conversation_detail','consult_home') )
AND page_name!='search_result'--android埋点会在上报search_result_more时重复上报search_result的埋点,导致page_stay重复计算
AND page_stay>=0 AND page_stay<1000
)t3
ON t2.partition_date=t3.partition_date
AND t2.cl_id=t3.cl_id
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
select distinct device_id
from ml.ml_d_ct_dv_devicespam_d
where partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
)t4
LATERAL VIEW explode(t4.channel) t5 AS channel
GROUP BY partition_date,device_os_type,active_type,t5.channel
)T9
ON T1.partition_date=T9.partition_date
AND T1.device_os_type=T9.device_os_type
AND T1.active_type=T9.active_type
AND T1.channel=T9.channel
ORDER BY day_id desc,device_os_type,active_type,is_ai_channel
SELECT
day_id as `日期`,
device_os_type as `设备类型`,
active_type as `活跃类型`,
card_content_type as `卡片类型`,
recommend_type as `推荐类型`,
NVL(CONCAT(ROUND((navbar_search+highlight_word+self_welfare_card+recommend_welfare_card+recommend_content_card/2)/card_exposure*100,2),'%'),0) as `来自首页推荐内容卡片的的有效二跳pv/首页卡片精准曝光PV`,
NVL(CONCAT(ROUND(card_click/card_exposure*100,2),'%'),0) as `首页卡片点击PV/首页卡片精准曝光PV`,
NVL(CONCAT(ROUND((navbar_search+highlight_word+self_welfare_card+recommend_welfare_card+recommend_content_card/2)/card_click*100,2),'%'),0) as `来自首页推荐内容卡片的的有效二跳pv/首页卡片点击PV`,
card_click as `首页卡片点击PV`,
card_exposure as `首页卡片精准曝光PV`,
(navbar_search+highlight_word+self_welfare_card+recommend_welfare_card+recommend_content_card/2)as `有效二跳pv`,
avg_page_stay as `来自I的单PV平均浏览时长`,
navbar_search as `来自I的搜索框+搜索按钮点击PV`,
highlight_word as `来自I的文内搜索点击PV`,
self_welfare_card as `来自I的商品卡片点击PV`,
recommend_welfare_card as `来自I的推荐商品+查看全部商品点击pv`,
recommend_content_card as `来自I的推荐内容点击pv`,
'未配置' as `来自I的推荐专题点击pv`,
'未上线' as `来自I的转诊点击pv`,
'未上线' as `来自I的视频面诊点击pv`
FROM pm.tl_pm_recommend_strategy_d
WHERE partition_day>='20200627' and partition_day<=regexp_replace(DATE_SUB(current_date,1) ,'-','')
order by `日期` desc ,`设备类型`,`活跃类型`,`卡片类型`,`推荐类型`
SET mapreduce.job.queuename=data;
SET mapreduce.map.memory.mb=8192;
SET mapreduce.map.java.opts=-Xmx8000m;
SET mapreduce.reduce.memory.mb=8192;
SET mapreduce.reduce.java.opts=-Xmx8000m;
set hive.auto.convert.join=true;
SET mapred.reduce.tasks=20;
SET role admin;
ADD JAR hdfs:///user/hive/share/lib/udf/hive-udf-1.0-SNAPSHOT.jar;
CREATE TEMPORARY FUNCTION convup AS 'com.gmei.hive.common.udf.UDFConvUpgrade';
INSERT OVERWRITE TABLE pm.tl_pm_recommend_strategy_d PARTITION (PARTITION_DAY = ${partition_day})
SELECT
t1.partition_date as day_id,
t1.device_os_type as device_os_type,
t1.active_type as active_type,
t2.card_content_type as card_content_type,
t2.recommend_type as recommend_type,
NVL(sum(t3.session_pv),0) as card_click,
NVL(sum(t2.session_pv),0) as card_exposure,
NVL(round(sum(page_stay)/count(distinct t4.cl_id)/60,2),0) as avg_page_stay,
NVL(sum(navbar_pv),0) as navbar_search,
NVL(sum(highlight_pv),0) as highlight_word,
NVL(sum(self_wel_pv),0) as self_welfare_card,
NVL(sum(recom_wel_pv),0)-NVL(sum(self_wel_pv),0) as recommend_welfare_card,--需要排除关联的商品卡片点击
NVL(sum(recom_content_pv),0) as recommend_content_card,
NULL as recommend_special_card,
NULL as transfer_card,
NULL as video_consultation
FROM
(
SELECT partition_date
,device_os_type
,CASE WHEN active_type = '4' THEN '老活'
WHEN active_type IN ('1','2') THEN '新增' END AS active_type
,device_id
FROM online.ml_device_day_active_status
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND active_type IN ('1','2','4')
AND first_channel_source_type not IN ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not LIKE 'promotion\_jf\_%'
)t1
JOIN
(--精准曝光,卡片id和session_id去重
SELECT partition_date,
card_content_type,
cl_id,
recommend_type,
card_id,
count(distinct app_session_id) as session_pv
FROM
(
SELECT partition_date,
cl_id,
case when card_content_type in ('qa','answer') then 'qa' else card_content_type end as card_content_type,
CASE WHEN transaction_type in ('ctr') THEN 'ctr预估'
WHEN transaction_type in ('cvr') THEN 'cvr预估'
WHEN transaction_type in ('-1','smr') THEN 'smr'
when transaction_type in ('pgc','hotspot') then '热点卡片'
when transaction_type in ('newdata') then '保量卡片'
END AS recommend_type,
card_id,
app_session_id
from online.ml_community_precise_exposure_detail
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
AND is_exposure = '1' ----精准曝光
AND page_name ='home'
AND tab_name = '精选'
AND transaction_type in ('-1','ctr','smr','cvr','hotspot','pgc','newdata')
AND card_content_type in ('qa','diary','user_post','answer')
group by partition_date,
case when card_content_type in ('qa','answer') then 'qa' else card_content_type end,
cl_id,
CASE WHEN transaction_type in ('ctr') THEN 'ctr预估'
WHEN transaction_type in ('cvr') THEN 'cvr预估'
WHEN transaction_type in ('-1','smr') THEN 'smr'
when transaction_type in ('pgc','hotspot') then '热点卡片'
when transaction_type in ('newdata') then '保量卡片' END,
card_id,
app_session_id
)a
group by partition_date,card_content_type,cl_id,recommend_type,card_id
)t2
on t1.device_id=t2.cl_id and t1.partition_date=t2.partition_date
LEFT JOIN
(--卡片,卡片id和session_id去重
SELECT partition_date,
card_content_type,
cl_id,
recommend_type,
card_id,
count(distinct app_session_id) as session_pv
FROM
(
SELECT partition_date,
cl_id,
case when params['card_content_type'] in ('qa','answer') then 'qa' else params['card_content_type'] end as card_content_type,
CASE WHEN params['transaction_type'] in ('ctr') THEN 'ctr预估'
WHEN params['transaction_type'] in ('cvr') THEN 'cvr预估'
WHEN params['transaction_type'] in ('-1','smr') THEN 'smr'
when params['transaction_type'] in ('pgc','hotspot') then '热点卡片'
when params['transaction_type'] in ('newdata') then '保量卡片'
END AS recommend_type,
params['card_id'] as card_id,
app_session_id
from online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action='on_click_card'
AND params['page_name'] ='home'
AND params['tab_name'] = '精选'
AND params['transaction_type'] in ('-1','ctr','smr','cvr','hotspot','pgc','newdata')
AND params['card_content_type'] in ('qa','diary','user_post','answer')
GROUP BY partition_date,
cl_id,
case when params['card_content_type'] in ('qa','answer') then 'qa' else params['card_content_type'] end,
CASE WHEN params['transaction_type'] in ('ctr') THEN 'ctr预估'
WHEN params['transaction_type'] in ('cvr') THEN 'cvr预估'
WHEN params['transaction_type'] in ('-1','smr') THEN 'smr'
when params['transaction_type'] in ('pgc','hotspot') then '热点卡片'
when params['transaction_type'] in ('newdata') then '保量卡片' END,
params['card_id'],
app_session_id
)a
group by partition_date,card_content_type,cl_id,recommend_type,card_id
)t3
on t2.partition_date=t3.partition_date
and t2.cl_id=t3.cl_id
and t2.card_id=t3.card_id
and t2.card_content_type=t3.card_content_type
and t2.recommend_type=t3.recommend_type
LEFT JOIN
(--页面浏览时长
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
sum(page_stay) as page_stay
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action='page_view'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND referrer='home'
AND page_stay>=0 AND page_stay<1000
GROUP BY partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)t4
on t4.partition_date=t3.partition_date
and t4.cl_id=t3.cl_id
and t4.business_id=t3.card_id
and t4.page_name=t3.card_content_type
LEFT JOIN
(--搜索框和点击行为
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as navbar_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action in ('on_click_navbar_search','do_search')
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)t5
on t5.partition_date=t3.partition_date
and t5.cl_id=t3.cl_id
and t5.business_id=t3.card_id
and t5.page_name=t3.card_content_type
LEFT JOIN
(--点击高亮词
SELECT partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as highlight_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action='on_click_card'
and params['card_type']='highlight_word'
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)t6
on t6.partition_date=t3.partition_date
and t6.cl_id=t3.cl_id
and t6.business_id=t3.card_id
and t6.page_name=t3.card_content_type
LEFT JOIN
(--关联的美购卡片
SELECT partition_date,cl_id,business_id,page_name,count(distinct app_session_id) as self_wel_pv
FROM
(
SELECT partition_date,cl_id,business_id,app_session_id,params['card_id'] as card_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND (get_json_object(params['extra_param'], '$.type')='交互栏'
or get_json_object(params['extra_param'], '$.jump_from')='msg_link'
or params['in_page_pos']='top' or params['in_page_pos']='bottom')
AND action='on_click_card'
and params['card_content_type']='service'
AND page_name IN ('diary_detail','topic_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,app_session_id,params['card_id'],
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)a
group by partition_date,cl_id,business_id,page_name
)t7
on t7.partition_date=t3.partition_date
and t7.cl_id=t3.cl_id
and t7.business_id=t3.card_id
and t7.page_name=t3.card_content_type
LEFT JOIN
(--推荐的美购卡片(需要排除作者消费的美购)
SELECT partition_date,cl_id,business_id,page_name,count(distinct app_session_id) as recom_wel_pv
FROM
(
SELECT partition_date,cl_id,business_id,app_session_id,params['card_id'] as card_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as service_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND (action='on_click_card'and params['card_content_type']='service'
or action='on_click_button' and params['button_name']='unfold')
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,app_session_id,params['card_id'],
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)a
group by partition_date,cl_id,business_id,page_name
)t8
on t8.partition_date=t3.partition_date
and t8.cl_id=t3.cl_id
and t8.business_id=t3.card_id
and t8.page_name=t3.card_content_type
LEFT JOIN
(--推荐的内容卡片
SELECT partition_date,cl_id,business_id,page_name,count(distinct app_session_id) as recom_content_pv
FROM
(
SELECT partition_date,cl_id,business_id,app_session_id,params['card_id'] as card_id,
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end as page_name,
count(1) as service_pv
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND action='on_click_card'
and params['card_content_type'] in ('qa','diary','user_post','answer')
AND page_name IN ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail')
AND (referrer='home' or
(params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
group by partition_date,cl_id,business_id,app_session_id,params['card_id'],
case when page_name in ('diary_detail','topic_detail') then 'diary'
when page_name in ('post_detail','user_post_detail','doctor_post_detail') then 'user_post'
when page_name in ('question_detail','answer_detail','question_answer_detail') then 'qa' else null end
)a
group by partition_date,cl_id,business_id,page_name
)t9
on t9.partition_date=t3.partition_date
and t9.cl_id=t3.cl_id
and t9.business_id=t3.card_id
and t9.page_name=t3.card_content_type
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=regexp_replace(DATE_SUB(current_date,1) ,'-','')
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.cl_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>=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
)t1
JOIN
( --医生账号
SELECT distinct user_id
FROM online.tl_hdfs_doctor_view
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
--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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
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 = regexp_replace(DATE_SUB(current_date,1) ,'-','')
) t1
JOIN
(
SELECT device_id
FROM online.ml_device_history_detail
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
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
on t2.partition_date=dev.partition_date and t2.cl_id=dev.device_id
WHERE spam_pv.device_id IS NULL
and dev.device_id is null
GROUP BY t1.partition_date,t1.device_os_type,t1.active_type,t2.card_content_type,t2.recommend_type
order by day_id,device_os_type,active_type,card_content_type,recommend_type;
\ No newline at end of file
SET mapreduce.job.queuename=data;
SET mapreduce.map.memory.mb=8192;
SET mapreduce.map.java.opts=-Xmx8000m;
SET mapreduce.reduce.memory.mb=8192;
SET mapreduce.reduce.java.opts=-Xmx8000m;
set hive.auto.convert.join=true;
SET mapred.reduce.tasks=20;
SET role admin;
INSERT OVERWRITE TABLE pm.tl_pm_search_click_path_d PARTITION (PARTITION_DAY = ${partition_day})
SELECT day_id as day_id
,device_os_type as device_os_type
,active_type as active_type
,v.search_entrance as search_entrance
,sum(search_pv) as click_search_pv
,sum(search_uv) as click_search_uv
FROM
(
SELECT day_id,device_os_type,active_type,array(search_entrance,'合计') as search_entrance
,search_pv,search_uv
FROM
(
SELECT t1.partition_date as day_id
,t1.device_os_type
,t1.active_type
,case when action='on_click_navbar_search' and page_name='home' then '首页搜索框'
when action='on_click_navbar_search' and page_name='welfare_home' then '美购首页搜索框'
when action='on_click_navbar_search' and page_name='category' then '品类聚合页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["home","category"]' then '来自品类聚合的美购列表页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["welfare_home"]' then '来自美购首页的美购列表页搜索框'
when action in ('do_search','on_click_navbar_search')
and page_name in ('diary_detail','topic_detail','post_detail','user_post_detail'
,'doctor_post_detail','question_detail','answer_detail','question_answer_detail') then '内容详情页搜索框'
when action ='详情页高亮词' then '详情页高亮词搜索'
when action='大家都在看' then '首页feed大家都在看'
when action='热搜词' then '美购首页热搜词' else null end as search_entrance
,count(cl_id) as search_pv
,count(distinct cl_id) as search_uv
FROM
(
SELECT partition_date,device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,device_id
FROM online.ml_device_day_active_status
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
join
(
SELECT partition_date,cl_id,page_name,action,params['referrer_link'] as referrer_link
FROM online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and action in ('do_search','on_click_navbar_search')
union all
SELECT partition_date,cl_id,null as page_name,'大家都���看' as action, null as referrer_link
FROM online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND params['in_page_pos']='猜你喜欢'
AND params['tab_name']='精选'
AND params['card_type']='search_word'
--AND page_name='home' android的page_name为空
union all
SELECT partition_date,cl_id,page_name,'热搜词' as action, null as referrer_link
FROM online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND page_name='welfare_home'
AND params['card_type'] ='search_word'
AND params['in_page_pos']='大家都在搜'
union all
select partition_date,cl_id,null as page_name,'详情页高亮词' as action,null as referrer_link
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and action='on_click_card'
and params['card_type']='highlight_word'
)t2
on t1.partition_date=t2.partition_date and t1.device_id=t2.cl_id
group by t1.partition_date
,t1.device_os_type
,t1.active_type
,case when action='on_click_navbar_search' and page_name='home' then '首页搜索框'
when action='on_click_navbar_search' and page_name='welfare_home' then '美购首页搜索框'
when action='on_click_navbar_search' and page_name='category' then '品类聚合页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["home","category"]' then '来自品类聚合的美购列表页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["welfare_home"]' then '来自美购首页的美购列表页搜索框'
when action in ('do_search','on_click_navbar_search')
and page_name in ('diary_detail','topic_detail','post_detail','user_post_detail'
,'doctor_post_detail','question_detail','answer_detail','question_answer_detail') then '内容详情页搜索框'
when action ='详情页高亮词' then '详情页高亮词搜索'
when action='大家都在看' then '首页feed大家都在看'
when action='热搜词' then '美购首页热搜词' else null end
having search_entrance is not null
)t
)n
LATERAL VIEW explode(n.search_entrance) v AS search_entrance
group by day_id,device_os_type,active_type,v.search_entrance;
\ No newline at end of file
--美购详情页的分发
SELECT `日期`,`设备类型`,`活跃类型`,`渠道`
,`美购详情页浏览pv`
,(`加购物车点击pv`+`评价列表页点击pv`+`立即支付点击pv`+`私信及电话咨询pv` +`选择美购项目点击pv`
+`机构主页点击pv`+`机构的其他美购点击pv`+`推荐美购点击pv`+`收藏点击pv`
+`右上角购物车点击pv`+`医生主页点击pv`+`分享点击pv`+`机构导航点击pv`) as `美购详情页分发pv加总`
,concat(round((`加购物车点击pv`+`评价列表页点击pv`+`立即支付点击pv`+`私信及电话咨询pv` +`选择美购项目点击pv`
+`机构主页点击pv`+`机构的其他美购点击pv`+`推荐美购点击pv`+`收藏点击pv`
+`右上角购物车点击pv`+`医生主页点击pv`+`分享点击pv`+`机构导航点击pv`)/`美购详情页浏览pv`*100,2),'%') as `美购详情页分发pv占比加总`
,`加购物车点击pv`
,concat(round(`加购物车点击pv`/`美购详情页浏览pv`*100,2),'%') as `加购物车点击pv占比`
,`评价列表页点击pv`
,concat(round(`评价列表页点击pv`/`美购详情页浏览pv`*100,2),'%') as `评价列表页点击pv占比`
,`立即支付点击pv`
,concat(round(`立即支付点击pv`/`美购详情页浏览pv`*100,2),'%') as `立即支付点击pv占比`
,`私信及电话咨询pv`
,concat(round(`私信及电话咨询pv`/`美购详情页浏览pv`*100,2),'%') as `私信及电话咨询pv占比`
,`选择美购项目点击pv`
,concat(round(`选择美购项目点击pv`/`美购详情页浏览pv`*100,2),'%') as `选择美购项目点击pv占比`
,`机构主页点击pv`
,concat(round(`机构主页点击pv`/`美购详情页浏览pv`*100,2),'%') as `机构主页点击pv占比`
,`机构的其他美购点击pv`
,concat(round(`机构的其他美购点击pv`/`美购详情页浏览pv`*100,2),'%') as `机构的其他美购点击pv占比`
,`推荐美购点击pv`
,concat(round(`推荐美购点击pv`/`美购详情页浏览pv`*100,2),'%') as `推荐美购点击pv占比`
,`收藏点击pv`
,concat(round(`收藏点击pv`/`美购详情页浏览pv`*100,2),'%') as `收藏点击pv占比`
,`右上角购物车点击pv`
,concat(round(`右上角购物车点击pv`/`美购详情页浏览pv`*100,2),'%') as `右上角购物车点击pv占比`
,`医生主页点击pv`
,concat(round(`医生主页点击pv`/`美购详情页浏览pv`*100,2),'%') as `医生主页点击pv占比`
,`分享点击pv`
,concat(round(`分享点击pv`/`美购详情页浏览pv`*100,2),'%') as `分享点击pv占比`
,`机构导航点击pv`
,concat(round(`机构导航点击pv`/`美购详情页浏览pv`*100,2),'%') as `机构导航点击pv占比`
FROM
(
SELECT t1.partition_date as `日期`
,t1.device_type as `设备类型`
,t1.active_type as `活跃类型`
,t2.channel as `渠道`
,count(case when type='美购详情页' then cl_id end ) as `美购详情页浏览pv`
,count(case when type='加购物车' then cl_id end ) as `加购物车点击pv`
,count(case when type='评价列表页' then cl_id end ) as `评价列表页点击pv`
,count(case when type='立即支付' then cl_id end ) as `立即支付点击pv`
,count(case when type='私信及电话咨询' then cl_id end ) as `私信及电话咨询pv`
,count(case when type='选择美购项目' then cl_id end ) as `选择美购项目点击pv`
,count(case when type='机构主页' then cl_id end ) as `机构主页点击pv`
,count(case when type='机构的其他美购' then cl_id end ) as `机构的其他美购点击pv`
,count(case when type='推荐美购' then cl_id end ) as `推荐美购点击pv`
,count(case when type='收藏' then cl_id end ) as `收藏点击pv`
,count(case when type='右上角购物车' then cl_id end ) as `右上角购物车点击pv`
,count(case when type='医生主页' then cl_id end ) as `医生主页点击pv`
,count(case when type='分享' then cl_id end ) as `分享点击pv`
,count(case when type='机构导航' then cl_id end ) as `机构导航点击pv`
FROM
(
SELECT click.partition_date,click.cl_id,click.type,mas.active_type,mas.device_type,mas.channel
FROM
( --浏览需要去掉疑似机构刷量的设备
SELECT pv.partition_date as partition_date,pv.cl_id as cl_id,type
FROM
(
SELECT partition_date,cl_id,'美购详情页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='page_view'
)pv
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on pv.cl_id=spam_pv.cl_id
WHERE spam_pv.cl_id IS NULL
UNION ALL
SELECT partition_date,cl_id, '加购物车' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date>=regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date<regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='welfare_multiattribute_click_add'
UNION ALL
SELECT partition_date,cl_id, '右上角购物车' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_navbar_cart'
UNION ALL
--点击查看更多评论
SELECT partition_date,cl_id, '评价列表页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_comment'
UNION ALL
--点击外显的评价标签
SELECT partition_date,cl_id, '评价列表页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='service_comment_click_tag'
UNION ALL
--点击外显的日记卡片
SELECT partition_date,cl_id, '评价列表页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='welfare_detail_comment_click_diary_card'
UNION ALL
SELECT partition_date,cl_id, '立即支付' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='welfare_multiattribute_click_buy'
UNION ALL
--点击选择更美项目
SELECT partition_date,cl_id, '选择美购项目' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name']='sku_choose'
UNION ALL
--7.22新版本--点击外露的美购项目
SELECT partition_date,cl_id, '选择美购项目' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name']='service_sku'
UNION ALL
--7.22新版本--点击查看更多
SELECT partition_date,cl_id, '选择美购项目' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name']='sku_all'
UNION ALL
--点击私信按钮
SELECT partition_date,cl_id, '私信及电话咨询' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_message'
UNION ALL
--7.20之后灰度上线的快捷咨询按钮和预约面诊按钮
SELECT partition_date,cl_id, '私信及电话咨询' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name'] in ('question_tag','appointment')
UNION ALL
--点击机构下面的在线咨询和电话咨询
SELECT partition_date,cl_id, '私信及电话咨询' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_curearea_contact'
AND params['connect_type'] in ('onlineconsult','phone')
UNION ALL
SELECT partition_date,cl_id, '机构主页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_curearea'
AND params['cure_type']='organization'
UNION ALL
SELECT partition_date,cl_id, '机构的其他美购' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_seller_service_item'
UNION ALL
SELECT partition_date,cl_id, '机构导航' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_address'
UNION ALL
SELECT partition_date,cl_id, '推荐美购' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date <regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_card'
AND params['card_content_type']='service'
AND params['tab_name']='推荐'
UNION ALL
SELECT partition_date,cl_id, '收藏' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_favor'
AND params['favor_type']='service'
AND params['motion']='do'
UNION ALL
SELECT partition_date,cl_id, '医生主页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_curearea'
AND params['cure_type']='doctor'
UNION ALL
SELECT partition_date,cl_id, '分享' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='page_click_share'
)click
JOIN
(
SELECT partition_date,device_os_type as device_type,m.device_id
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20190101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)mas
ON click.cl_id=mas.device_id
AND click.partition_date=mas.partition_date
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY t1.partition_date,t1.device_type,t1.active_type,t2.channel
)T1
ORDER BY `日期` desc,`设备类型`,`活跃类型`,`渠道`
--美购详情页的分发
SELECT `日期`,`设备类型`,`活跃类型`,`渠道`
,`美购详情页浏览uv`
,(`加购物车点击uv`+`评价列表页点击uv`+`立即支付点击uv`+`私信及电话咨询uv` +`选择美购项目点击uv`
+`机构主页点击uv`+`机构的其他美购点击uv`+`推荐美购点击uv`+`收藏点击uv`
+`右上角购物车点击uv`+`医生主页点击uv`+`分享点击uv`+`机构导航点击uv`) as `美购详情页分发uv加总`
,concat(round((`加购物车点击uv`+`评价列表页点击uv`+`立即支付点击uv`+`私信及电话咨询uv` +`选择美购项目点击uv`
+`机构主页点击uv`+`机构的其他美购点击uv`+`推荐美购点击uv`+`收藏点击uv`
+`右上角购物车点击uv`+`医生主页点击uv`+`分享点击uv`+`机构导航点击uv`)/`美购详情页浏览uv`*100,2),'%') as `美购详情页分发uv占比加总`
,`加购物车点击uv`
,concat(round(`加购物车点击uv`/`美购详情页浏览uv`*100,2),'%') as `加购物车点击uv占比`
,`评价列表页点击uv`
,concat(round(`评价列表页点击uv`/`美购详情页浏览uv`*100,2),'%') as `评价列表页点击uv占比`
,`立即支付点击uv`
,concat(round(`立即支付点击uv`/`美购详情页浏览uv`*100,2),'%') as `立即支付点击uv占比`
,`私信及电话咨询uv`
,concat(round(`私信及电话咨询uv`/`美购详情页浏览uv`*100,2),'%') as `私信及电话咨询uv占比`
,`选择美购项目点击uv`
,concat(round(`选择美购项目点击uv`/`美购详情页浏览uv`*100,2),'%') as `选择美购项目点击uv占比`
,`机构主页点击uv`
,concat(round(`机构主页点击uv`/`美购详情页浏览uv`*100,2),'%') as `机构主页点击uv占比`
,`机构的其他美购点击uv`
,concat(round(`机构的其他美购点击uv`/`美购详情页浏览uv`*100,2),'%') as `机构的其他美购点击uv占比`
,`推荐美购点击uv`
,concat(round(`推荐美购点击uv`/`美购详情页浏览uv`*100,2),'%') as `推荐美购点击uv占比`
,`收藏点击uv`
,concat(round(`收藏点击uv`/`美购详情页浏览uv`*100,2),'%') as `收藏点击uv占比`
,`右上角购物车点击uv`
,concat(round(`右上角购物车点击uv`/`美购详情页浏览uv`*100,2),'%') as `右上角购物车点击uv占比`
,`医生主页点击uv`
,concat(round(`医生主页点击uv`/`美购详情页浏览uv`*100,2),'%') as `医生主页点击uv占比`
,`分享点击uv`
,concat(round(`分享点击uv`/`美购详情页浏览uv`*100,2),'%') as `分享点击uv占比`
,`机构导航点击uv`
,concat(round(`机构导航点击uv`/`美购详情页浏览uv`*100,2),'%') as `机构导航点击uv占比`
FROM
(
SELECT t1.partition_date as `日期`
,t1.device_type as `设备类型`
,t1.active_type as `活跃类型`
,t2.channel as `渠道`
,count(case when type='美购详情页' then cl_id end ) as `美购详情页浏览uv`
,count(case when type='加购物车' then cl_id end ) as `加购物车点击uv`
,count(case when type='评价列表页' then cl_id end ) as `评价列表页点击uv`
,count(case when type='立即支付' then cl_id end ) as `立即支付点击uv`
,count(case when type='私信及电话咨询' then cl_id end ) as `私信及电话咨询uv`
,count(case when type='选择美购项目' then cl_id end ) as `选择美购项目点击uv`
,count(case when type='机构主页' then cl_id end ) as `机构主页点击uv`
,count(case when type='机构的其他美购' then cl_id end ) as `机构的其他美购点击uv`
,count(case when type='推荐美购' then cl_id end ) as `推荐美购点击uv`
,count(case when type='收藏' then cl_id end ) as `收藏点击uv`
,count(case when type='右上角购物车' then cl_id end ) as `右上角购物车点击uv`
,count(case when type='医生主页' then cl_id end ) as `医生主页点击uv`
,count(case when type='分享' then cl_id end ) as `分享点击uv`
,count(case when type='机构导航' then cl_id end ) as `机构导航点击uv`
FROM
(
SELECT click.partition_date,click.cl_id,click.type,mas.active_type,mas.device_type,mas.channel
FROM
( --浏览需要去掉疑似机构刷量的设备
SELECT uv.partition_date as partition_date,uv.cl_id as cl_id,type
FROM
(
SELECT partition_date,cl_id,'美购详情页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='page_view'
)uv
LEFT JOIN
( -- 去掉疑似机构刷量的UV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on uv.cl_id=spam_pv.cl_id
WHERE spam_pv.cl_id IS NULL
UNION ALL
SELECT partition_date,cl_id, '加购物车' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='welfare_multiattribute_click_add'
UNION ALL
SELECT partition_date,cl_id, '右上角购物车' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_navbar_cart'
UNION ALL
--点击查看更多评论
SELECT partition_date,cl_id, '评价列表页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_comment'
UNION ALL
--点击外显的评价标签
SELECT partition_date,cl_id, '评价列表页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='service_comment_click_tag'
UNION ALL
--点击外显的日记卡片
SELECT partition_date,cl_id, '评价列表页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='welfare_detail_comment_click_diary_card'
UNION ALL
SELECT partition_date,cl_id, '立即支付' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='welfare_multiattribute_click_buy'
UNION ALL
--点击选择更美项目
SELECT partition_date,cl_id, '选择美购项目' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name']='sku_choose'
UNION ALL
--7.22新版本--点击外露的美购项目
SELECT partition_date,cl_id, '选择美购项目' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name']='service_sku'
UNION ALL
--7.22新版本--点击查看更多
SELECT partition_date,cl_id, '选择美购项目' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name']='sku_all'
UNION ALL
--点击私信按钮
SELECT partition_date,cl_id, '私信及电话咨询' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_message'
UNION ALL
--7.20之后灰度上线的快捷咨询按钮和预约面诊按钮
SELECT partition_date,cl_id, '私信及电话咨询' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name'] in ('question_tag','appointment')
UNION ALL
--点击机构下面的在线咨询和电话咨询
SELECT partition_date,cl_id, '私信及电话咨询' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_curearea_contact'
AND params['connect_type'] in ('onlineconsult','phone')
UNION ALL
SELECT partition_date,cl_id, '机构主页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_curearea'
AND params['cure_type']='organization'
UNION ALL
SELECT partition_date,cl_id, '机构的其他美购' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_seller_service_item'
UNION ALL
SELECT partition_date,cl_id, '机构导航' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_address'
UNION ALL
SELECT partition_date,cl_id, '推荐美购' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date <regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_card'
AND params['card_content_type']='service'
AND params['tab_name']='推荐'
UNION ALL
SELECT partition_date,cl_id, '收藏' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_favor'
AND params['favor_type']='service'
AND params['motion']='do'
UNION ALL
SELECT partition_date,cl_id, '医生主页' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_curearea'
AND params['cure_type']='doctor'
UNION ALL
SELECT partition_date,cl_id, '分享' as type
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='page_click_share'
)click
JOIN
(
SELECT partition_date,device_os_type as device_type,m.device_id
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20190101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)mas
ON click.cl_id=mas.device_id
AND click.partition_date=mas.partition_date
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY t1.partition_date,t1.device_type,t1.active_type,t2.channel
)T1
ORDER BY `日期` desc,`设备类型`,`活跃类型`,`渠道`
--美购详情页的来源
SELECT T1.partition_date as `日期`
,T1.device_type as `设备类型`
,T1.active_type as `活跃类型`
,T1.channel as `渠道`
,T1.wel_pv as `美购详情页pv`
,(T2.search_result_welfare_pv+T2.welfare_list_pv+T2.organization_detail_pv+T2.category_pv+T2.sign_pv
+T2.special_pv+T2.my_cart_pv+T2.search_result_more_pv+T2.welfare_home_pv+T2.conversation_detail_pv
+T2.wel_pv+T2.order_detail_pv+T2.expert_detail_pv+T2.ai_report_pv+T2.diary_detail_pv+T2.zone_pv) as `转化美购pv总量`
,concat(round((T2.search_result_welfare_pv+T2.welfare_list_pv+T2.organization_detail_pv+T2.category_pv+T2.sign_pv
+T2.special_pv+T2.my_cart_pv+T2.search_result_more_pv+T2.welfare_home_pv+T2.conversation_detail_pv
+T2.wel_pv+T2.order_detail_pv+T2.expert_detail_pv+T2.ai_report_pv+T2.diary_detail_pv+T2.zone_pv)/T1.wel_pv*100,2),'%') as `转化美购pv占比加总`
,T1.search_result_welfare_pv as `搜索结果美购页pv`
,T2.search_result_welfare_pv as `搜索结果美购页-转化pv`
,T3.result_wel_add_pv as `搜索结果美购页-转化点击加车pv`
,T3.result_wel_buy_pv as `搜索结果美购页-转化点击立即支付pv`
,T3.result_wel_msg_pv as `搜索结果美购页-转化点击私信咨询pv`
,concat(round(T2.search_result_welfare_pv/T1.search_result_welfare_pv*100,2),'%') as `搜索结果美购页-转化pv率`
,concat(round(T2.search_result_welfare_pv/T1.wel_pv*100,2),'%') as `搜索结果美购页-转化美购pv占比`
,concat(round(T3.result_wel_add_pv/T2.search_result_welfare_pv*100,2),'%') as `搜索结果美购页-点击加车率`
,concat(round(T3.result_wel_buy_pv/T2.search_result_welfare_pv*100,2),'%') as `搜索结果美购页-点击立即支付率`
,concat(round(T3.result_wel_msg_pv/T2.search_result_welfare_pv*100,2),'%') as `搜索结果美购页-点击私信咨询率`
,T1.organization_detail_pv as `医院主页pv`
,T2.organization_detail_pv as `医院主页-转化pv`
,T3.org_add_pv as `医院主页-转化点击加车pv`
,T3.org_buy_pv as `医院主页-转化点击立即支付pv`
,T3.org_msg_pv as `医院主页-转化点击私信咨询pv`
,concat(round(T2.organization_detail_pv/T1.organization_detail_pv*100,2),'%') as `医院主页-转化pv率`
,concat(round(T2.organization_detail_pv/T1.wel_pv*100,2),'%') as `医院主页-转化美购pv占比`
,concat(round(T3.org_add_pv/T2.organization_detail_pv*100,2),'%') as `医院主页-点击加车率`
,concat(round(T3.org_buy_pv/T2.organization_detail_pv*100,2),'%') as `医院主页-点击立即支付率`
,concat(round(T3.org_msg_pv/T2.organization_detail_pv*100,2),'%') as `医院主页-点击私信咨询率`
,T1.category_pv as `品类聚合页pv`
,T2.category_pv as `品类聚合页-转化pv`
,T3.category_add_pv as `品类聚合页-转化点击加车pv`
,T3.category_buy_pv as `品类聚合页-转化点击立即支付pv`
,T3.category_msg_pv as `品类聚合页-转化点击私信咨询pv`
,concat(round(T2.category_pv/T1.category_pv*100,2),'%') as `品类聚合页-转化pv率`
,concat(round(T2.category_pv/T1.wel_pv*100,2),'%') as `品类聚合页-转化美购pv占比`
,concat(round(T3.category_add_pv/T2.category_pv*100,2),'%') as `品类聚合页-点击加车率`
,concat(round(T3.category_buy_pv/T2.category_pv*100,2),'%') as `品类聚合页-点击立即支付率`
,concat(round(T3.category_msg_pv/T2.category_pv*100,2),'%') as `品类聚合页-点击私信咨询率`
,T1.conversation_detail_pv as `私信详情页pv`
,T2.conversation_detail_pv as `私信详情页-转化pv`
,T3.conv_add_pv as `私信详情页-转化点击加车pv`
,T3.conv_buy_pv as `私信详情页-转化点击立即支付pv`
,T3.conv_msg_pv as `私信详情页-转化点击私信咨询pv`
,concat(round(T2.conversation_detail_pv/T1.conversation_detail_pv*100,2),'%') as `私信详情页-转化pv率`
,concat(round(T2.conversation_detail_pv/T1.wel_pv*100,2),'%') as `私信详情页-转化美购pv占比`
,concat(round(T3.conv_add_pv/T2.conversation_detail_pv*100,2),'%') as `私信详情页-点击加车率`
,concat(round(T3.conv_buy_pv/T2.conversation_detail_pv*100,2),'%') as `私信详情页-点击立即支付率`
,concat(round(T3.conv_msg_pv/T2.conversation_detail_pv*100,2),'%') as `私信详情页-点击私信咨询率`
,T1.welfare_list_pv as `美购列表页pv`
,T2.welfare_list_pv as `美购列表页-转化pv`
,T3.wel_list_add_pv as `美购列表页-转化点击加车pv`
,T3.wel_list_buy_pv as `美购列表页-转化点击立即支付pv`
,T3.wel_list_msg_pv as `美购列表页-转化点击私信咨询pv`
,concat(round(T2.welfare_list_pv/T1.welfare_list_pv*100,2),'%') as `美购列表页-转化pv率`
,concat(round(T2.welfare_list_pv/T1.wel_pv*100,2),'%') as `美购列表页-转化美购pv占比`
,concat(round(T3.wel_list_add_pv/T2.welfare_list_pv*100,2),'%') as `美购列表页-点击加车率`
,concat(round(T3.wel_list_buy_pv/T2.welfare_list_pv*100,2),'%') as `美购列表页-点击立即支付率`
,concat(round(T3.wel_list_msg_pv/T2.welfare_list_pv*100,2),'%') as `美购列表页-点击私信咨询率`
,T1.my_cart_pv as`购物车pv`
,T2.my_cart_pv as`购物车-转化pv`
,T3.cart_add_pv as `购物车-转化点击加车pv`
,T3.cart_buy_pv as `购物车-转化点击立即支付pv`
,T3.cart_msg_pv as `购物车-转化点击私信咨询pv`
,concat(round(T2.my_cart_pv/T1.my_cart_pv*100,2),'%') as `购物车-转化pv率`
,concat(round(T2.my_cart_pv/T1.wel_pv*100,2),'%') as `购物车-转化美购pv占比`
,concat(round(T3.cart_add_pv/T2.my_cart_pv*100,2),'%') as `购物车-点击加车率`
,concat(round(T3.cart_buy_pv/T2.my_cart_pv*100,2),'%') as `购物车-点击立即支付率`
,concat(round(T3.cart_msg_pv/T2.my_cart_pv*100,2),'%') as `购物车-点击私信咨询率`
,T1.search_result_more_pv as `搜索结果综合页pv`
,T2.search_result_more_pv as `搜索结果综合页-转化pv`
,T3.result_more_add_pv as `搜索结果综合页-转化点击加车pv`
,T3.result_more_buy_pv as `搜索结果综合页-转化点击立即支付pv`
,T3.result_more_msg_pv as `搜索结果综合页-转化点击私信咨询pv`
,concat(round(T2.search_result_more_pv/T1.search_result_more_pv*100,2),'%') as `搜索结果综合页-转化pv率`
,concat(round(T2.search_result_more_pv/T1.wel_pv*100,2),'%') as `搜索结果综合页-转化美购pv占比`
,concat(round(T3.result_more_add_pv/T2.search_result_more_pv*100,2),'%') as `搜索结果综合页-点击加车率`
,concat(round(T3.result_more_buy_pv/T2.search_result_more_pv*100,2),'%') as `搜索结果综合页-点击立即支付率`
,concat(round(T3.result_more_msg_pv/T2.search_result_more_pv*100,2),'%') as `搜索结果综合页-点击私信咨询率`
,T1.order_detail_pv as `订单详情页pv`
,T2.order_detail_pv as `订单详情页-转化pv`
,T3.order_add_pv as `订单详情页-转化点击加车pv`
,T3.order_buy_pv as `订单详情页-转化点击立即支付pv`
,T3.order_msg_pv as `订单详情页-转化点击私信咨询pv`
,concat(round(T2.order_detail_pv/T1.order_detail_pv*100,2),'%') as `订单详情页-转化pv率`
,concat(round(T2.order_detail_pv/T1.wel_pv*100,2),'%') as `订单详情页-转化美购pv占比`
,concat(round(T3.order_add_pv/T2.order_detail_pv*100,2),'%') as `订单详情页-点击加车率`
,concat(round(T3.order_buy_pv/T2.order_detail_pv*100,2),'%') as `订单详情页-点击立即支付率`
,concat(round(T3.order_msg_pv/T2.order_detail_pv*100,2),'%') as `订单详情页-点击私信咨询率`
,T1.special_pv as `专题和大促页pv`
,T2.special_pv as `专题和大促页-转化pv`
,T3.special_add_pv as `专题和大促页-转化点击加车pv`
,T3.special_buy_pv as `专题和大促页-转化点击立即支付pv`
,T3.special_msg_pv as `专题和大促页-转化点击私信咨询pv`
,concat(round(T2.special_pv/T1.special_pv*100,2),'%') as `专题和大促页-转化pv率`
,concat(round(T2.special_pv/T1.wel_pv*100,2),'%') as `专题和大促页-转化美购pv占比`
,concat(round(T3.special_add_pv/T2.special_pv*100,2),'%') as `专题和大促页-点击加车率`
,concat(round(T3.special_buy_pv/T2.special_pv*100,2),'%') as `专题和大促页-点击立即支付率`
,concat(round(T3.special_msg_pv/T2.special_pv*100,2),'%') as `专题和大促页-点击私信咨询率`
,T1.expert_detail_pv as `医生主页pv`
,T2.expert_detail_pv as `医生主页-转化pv`
,T3.exp_add_pv as `医生主页-转化点击加车pv`
,T3.exp_buy_pv as `医生主页-转化点击立即支付pv`
,T3.exp_msg_pv as `医生主页-转化点击私信咨询pv`
,concat(round(T2.expert_detail_pv/T1.expert_detail_pv*100,2),'%') as `医生主页-转化pv率`
,concat(round(T2.expert_detail_pv/T1.wel_pv*100,2),'%') as `医生主页-转化美购pv占比`
,concat(round(T3.exp_add_pv/T2.expert_detail_pv*100,2),'%') as `医生主页-点击加车率`
,concat(round(T3.exp_buy_pv/T2.expert_detail_pv*100,2),'%') as `医生主页-点击立即支付率`
,concat(round(T3.exp_msg_pv/T2.expert_detail_pv*100,2),'%') as `医生主页-点击私信咨询率`
,T1.wel_pv as `美购详情页pv`
,T2.wel_pv as `其他美购详情页-转化pv`
,T3.wel_add_pv as `其他美购详情页-转化点击加车pv`
,T3.wel_buy_pv as `其他美购详情页-转化点击立即支付pv`
,T3.wel_msg_pv as `其他美购详情页-转化点击私信咨询pv`
,concat(round(T2.wel_pv/T1.wel_pv*100,2),'%') as `其他美购详情页-转化pv率`
,concat(round(T2.wel_pv/T1.wel_pv*100,2),'%') as `其他美购详情页-转化美购pv占比`
,concat(round(T3.wel_add_pv/T2.wel_pv*100,2),'%') as `其他美购详情页-点击加车率`
,concat(round(T3.wel_buy_pv/T2.wel_pv*100,2),'%') as `其他美购详情页-点击立即支付率`
,concat(round(T3.wel_msg_pv/T2.wel_pv*100,2),'%') as `其他美购详情页-点击私信咨询率`
,T1.welfare_home_pv as `美购首页pv`
,T2.welfare_home_pv as `美购首页-转化pv`
,T3.wel_home_add_pv as `美购首页-转化点击加车pv`
,T3.wel_home_buy_pv as `美购首页-转化点击立即支付pv`
,T3.wel_home_msg_pv as `美购首页-转化点击私信咨询pv`
,concat(round(T2.welfare_home_pv/T1.welfare_home_pv*100,2),'%') as `美购首页-转化pv率`
,concat(round(T2.welfare_home_pv/T1.wel_pv*100,2),'%') as `美购首页-转化美购pv占比`
,concat(round(T3.wel_home_add_pv/T2.welfare_home_pv*100,2),'%') as `美购首页-点击加车率`
,concat(round(T3.wel_home_buy_pv/T2.welfare_home_pv*100,2),'%') as `美购首页-点击立即支付率`
,concat(round(T3.wel_home_msg_pv/T2.welfare_home_pv*100,2),'%') as `美购首页-点击私信咨询率`
,T1.diary_detail_pv as `日记本详情页pv`
,T2.diary_detail_pv as `日记本详情页-转化pv`
,T3.diary_add_pv as `日记本详情页-转化点击加车pv`
,T3.diary_buy_pv as `日记本详情页-转化点击立即支付pv`
,T3.diary_msg_pv as `日记本详情页-转化点击私信咨询pv`
,concat(round(T2.diary_detail_pv/T1.diary_detail_pv*100,2),'%') as `日记本详情页-转化pv率`
,concat(round(T2.diary_detail_pv/T1.wel_pv*100,2),'%') as `日记本详情页-转化美购pv占比`
,concat(round(T3.diary_add_pv/T2.diary_detail_pv*100,2),'%') as `日记本详情页-点击加车率`
,concat(round(T3.diary_buy_pv/T2.diary_detail_pv*100,2),'%') as `日记本详情页-点击立即支付率`
,concat(round(T3.diary_msg_pv/T2.diary_detail_pv*100,2),'%') as `日记本详情页-点击私信咨询率`
,T1.sign_pv as `签到页pv`
,T2.sign_pv as `签到页-转化pv`
,T3.sign_add_pv as `签到页-转化点击加车pv`
,T3.sign_buy_pv as `签到页-转化点击立即支付pv`
,T3.sign_msg_pv as `签到页-转化点击私信咨询pv`
,concat(round(T2.sign_pv/T1.sign_pv*100,2),'%') as `签到页-转化pv率`
,concat(round(T2.sign_pv/T1.wel_pv*100,2),'%') as `签到页-转化美购pv占比`
,concat(round(T3.sign_add_pv/T2.sign_pv*100,2),'%') as `签到页-点击加车率`
,concat(round(T3.sign_buy_pv/T2.sign_pv*100,2),'%') as `签到页-点击立即支付率`
,concat(round(T3.sign_msg_pv/T2.sign_pv*100,2),'%') as `签到页-点击私信咨询率`
,T1.ai_report_pv as `AI结果页pv`
,T2.ai_report_pv as `AI结果页-转化pv`
,T3.ai_add_pv as `AI结果页-转化点击加车pv`
,T3.ai_buy_pv as `AI结果页-转化点击立即支付pv`
,T3.ai_msg_pv as `AI结果页-转化点击私信咨询pv`
,concat(round(T2.ai_report_pv/T1.ai_report_pv*100,2),'%') as `AI结果页-转化pv率`
,concat(round(T2.ai_report_pv/T1.wel_pv*100,2),'%') as `AI结果页-转化美购pv占比`
,concat(round(T3.ai_add_pv/T2.ai_report_pv*100,2),'%') as `AI结果页-点击加车率`
,concat(round(T3.ai_buy_pv/T2.ai_report_pv*100,2),'%') as `AI结果页-点击立即支付率`
,concat(round(T3.ai_msg_pv/T2.ai_report_pv*100,2),'%') as `AI结果页-点击私信咨询率`
,T1.zone_pv as `内容聚合页pv`
,T2.zone_pv as `内容聚合页-转化pv`
,T3.zone_add_pv as `内容聚合页-转化点击加车pv`
,T3.zone_buy_pv as `内容聚合页-转化点击立即支付pv`
,T3.zone_msg_pv as `内容聚合页-转化点击私信咨询pv`
,concat(round(T2.zone_pv/T1.zone_pv*100,2),'%') as `内容聚合页-转化pv率`
,concat(round(T2.zone_pv/T1.wel_pv*100,2),'%') as `内容聚合页-转化美购pv占比`
,concat(round(T3.zone_add_pv/T2.zone_pv*100,2),'%') as `内容聚合页-点击加车率`
,concat(round(T3.zone_buy_pv/T2.zone_pv*100,2),'%') as `内容聚合页-点击立即支付率`
,concat(round(T3.zone_msg_pv/T2.zone_pv*100,2),'%') as `内容聚合页-点击私信咨询率`
FROM
(--能够走向美购详情页的各页面pv/uv
SELECT t1.partition_date
,t1.device_type
,t1.active_type
,t2.channel
,count(case when page_name = 'welfare_detail' then t1.cl_id end) as wel_pv
,count(case when page_name = 'search_result_more' then t1.cl_id end) as search_result_more_pv
,count(case when page_name = 'search_result_welfare' then t1.cl_id end) as search_result_welfare_pv
,count(case when page_name = 'organization_detail' then t1.cl_id end) as organization_detail_pv
,count(case when page_name = 'expert_detail' then t1.cl_id end) as expert_detail_pv
,count(case when page_name = 'category' then t1.cl_id end) as category_pv
,count(case when page_name = 'welfare_list' then t1.cl_id end) as welfare_list_pv
,count(case when page_name = 'welfare_home' then t1.cl_id end) as welfare_home_pv
,count(case when page_name = 'conversation_detail' then t1.cl_id end) as conversation_detail_pv
,count(case when page_name = 'my_cart' then t1.cl_id end) as my_cart_pv
,count(case when page_name = 'diary_detail' then t1.cl_id end) as diary_detail_pv
,count(case when page_name = 'order_detail' then t1.cl_id end) as order_detail_pv
,count(case when page_name ='new_sign' then t1.cl_id end) as sign_pv
,count(case when page_name in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') then t1.cl_id end) as special_pv --专题和大促
,count(case when page_name = 'zone_v3' then t1.cl_id end) as zone_pv
,count(case when page_name in ('report_result','face_detect_result') then t1.cl_id end) as ai_report_pv --待之后增加模拟整形页面
FROM
(
SELECT t1.partition_date,t1.page_name,t1.cl_id,mas.device_type,mas.active_type,mas.channel
FROM
(
SELECT partition_date,page_name,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='page_view'
)t1
JOIN
(
SELECT partition_date,device_os_type as device_type,m.device_id
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20190101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)mas
ON t1.cl_id=mas.device_id
AND t1.partition_date=mas.partition_date
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t1.cl_id=spam_pv.cl_id
WHERE spam_pv.cl_id IS NULL
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY t1.partition_date,t1.device_type,t1.active_type,t2.channel
)T1
LEFT JOIN
(--不同referrer下的美购详情页pv/uv
SELECT t1.partition_date
,t1.device_type
,t1.active_type
,t2.channel
,count(case when referrer = 'welfare_detail' then t1.cl_id end) as wel_pv
,count(case when referrer = 'search_result_more' then t1.cl_id end) as search_result_more_pv
,count(case when referrer = 'search_result_welfare' then t1.cl_id end) as search_result_welfare_pv
,count(case when referrer = 'organization_detail' then t1.cl_id end) as organization_detail_pv
,count(case when referrer = 'expert_detail' then t1.cl_id end) as expert_detail_pv
,count(case when referrer = 'category' then t1.cl_id end) as category_pv
,count(case when referrer = 'welfare_list' then t1.cl_id end) as welfare_list_pv
,count(case when referrer = 'welfare_home' then t1.cl_id end) as welfare_home_pv
,count(case when referrer = 'conversation_detail' then t1.cl_id end) as conversation_detail_pv
,count(case when referrer = 'my_cart' then t1.cl_id end) as my_cart_pv
,count(case when referrer = 'diary_detail' then t1.cl_id end) as diary_detail_pv
,count(case when referrer = 'order_detail' then t1.cl_id end) as order_detail_pv
,count(case when referrer ='new_sign' then t1.cl_id end) as sign_pv
,count(case when referrer in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') then t1.cl_id end) as special_pv --专题和大促
,count(case when referrer = 'zone_v3' then t1.cl_id end) as zone_pv
,count(case when referrer in ('report_result','face_detect_result') then t1.cl_id end) as ai_report_pv --待之后增加模拟整形页面
FROM
(
SELECT t1.partition_date,t1.referrer,t1.cl_id,mas.device_type,mas.active_type,mas.channel
FROM
(
SELECT partition_date,referrer,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='page_view'
)t1
JOIN
(
SELECT partition_date,device_os_type as device_type,m.device_id
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20190101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)mas
ON t1.cl_id=mas.device_id
AND t1.partition_date=mas.partition_date
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t1.cl_id=spam_pv.cl_id
WHERE spam_pv.cl_id IS NULL
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY t1.partition_date,t1.device_type,t1.active_type,t2.channel
)T2
ON T1.partition_date=T2.partition_date
and T1.device_type=T2.device_type
AND T1.active_type=T2.active_type
AND T1.channel=T2.channel
LEFT JOIN
(--点击加车/支付/私信的不同来源
SELECT t1.partition_date
,t1.device_type
,t1.active_type
,t2.channel
,count(case when referrer = 'welfare_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as wel_add_pv
,count(case when referrer = 'welfare_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as wel_buy_pv
,count(case when referrer = 'welfare_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as wel_msg_pv
,count(case when referrer = 'search_result_more' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as result_more_add_pv
,count(case when referrer = 'search_result_more' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as result_more_buy_pv
,count(case when referrer = 'search_result_more' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as result_more_msg_pv
,count(case when referrer = 'search_result_welfare' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as result_wel_add_pv
,count(case when referrer = 'search_result_welfare' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as result_wel_buy_pv
,count(case when referrer = 'search_result_welfare' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as result_wel_msg_pv
,count(case when referrer = 'organization_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as org_add_pv
,count(case when referrer = 'organization_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as org_buy_pv
,count(case when referrer = 'organization_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as org_msg_pv
,count(case when referrer = 'expert_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as exp_add_pv
,count(case when referrer = 'expert_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as exp_buy_pv
,count(case when referrer = 'expert_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as exp_msg_pv
,count(case when referrer = 'category' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as category_add_pv
,count(case when referrer = 'category' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as category_buy_pv
,count(case when referrer = 'category' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as category_msg_pv
,count(case when referrer = 'welfare_list' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as wel_list_add_pv
,count(case when referrer = 'welfare_list' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as wel_list_buy_pv
,count(case when referrer = 'welfare_list' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as wel_list_msg_pv
,count(case when referrer = 'welfare_home' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as wel_home_add_pv
,count(case when referrer = 'welfare_home' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as wel_home_buy_pv
,count(case when referrer = 'welfare_home' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as wel_home_msg_pv
,count(case when referrer = 'conversation_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as conv_add_pv
,count(case when referrer = 'conversation_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as conv_buy_pv
,count(case when referrer = 'conversation_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as conv_msg_pv
,count(case when referrer = 'my_cart' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as cart_add_pv
,count(case when referrer = 'my_cart' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as cart_buy_pv
,count(case when referrer = 'my_cart' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as cart_msg_pv
,count(case when referrer = 'diary_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as diary_add_pv
,count(case when referrer = 'diary_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as diary_buy_pv
,count(case when referrer = 'diary_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as diary_msg_pv
,count(case when referrer = 'order_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as order_add_pv
,count(case when referrer = 'order_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as order_buy_pv
,count(case when referrer = 'order_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as order_msg_pv
,count(case when referrer = 'new_sign' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as sign_add_pv
,count(case when referrer = 'new_sign' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as sign_buy_pv
,count(case when referrer = 'new_sign' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as sign_msg_pv
,count(case when referrer in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as special_add_pv
,count(case when referrer in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as special_buy_pv
,count(case when referrer in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as special_msg_pv
,count(case when referrer = 'zone_v3' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as zone_add_pv
,count(case when referrer = 'zone_v3' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as zone_buy_pv
,count(case when referrer = 'zone_v3' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as zone_msg_pv
,count(case when referrer in ('report_result','face_detect_result') and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as ai_add_pv
,count(case when referrer in ('report_result','face_detect_result') and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as ai_buy_pv
,count(case when referrer in ('report_result','face_detect_result') and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as ai_msg_pv
FROM
(
SELECT t1.partition_date,t1.referrer,t1.action,t1.cl_id,mas.device_type,mas.active_type,mas.channel
FROM
( --点击加车/支付
SELECT partition_date,referrer,action,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action in ('welfare_multiattribute_click_add','welfare_multiattribute_click_buy')
UNION ALL
--点击私信按钮
SELECT partition_date,referrer,action,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_message'
UNION ALL
--点击私信区域(目前referrer缺失,故通过拆解referrer_link的方式获得)
SELECT partition_date,referrer,action,cl_id
FROM
(
SELECT partition_date,cl_id,action,t2.referrer as referrer
,row_number () over (PARTITION BY t1.referrer_link,t1.cl_id ORDER BY t2.link_id desc) as rank
from
( SELECT partition_date,params['referrer_link'] as referrer_link,cl_id,action
,json_split(params['referrer_link'],'string') as a
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name'] in ('question_tag','appointment')
)t1
lateral view posexplode(a) t2 as link_id,referrer
)t3
where rank=1
)t1
JOIN
(
SELECT partition_date,device_os_type as device_type,m.device_id
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20190101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)mas
ON t1.cl_id=mas.device_id
AND t1.partition_date=mas.partition_date
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t1.cl_id=spam_pv.cl_id
WHERE spam_pv.cl_id IS NULL
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY t1.partition_date,t1.device_type,t1.active_type,t2.channel
)T3
ON T1.partition_date=T3.partition_date
and T1.device_type=T3.device_type
AND T1.active_type=T3.active_type
AND T1.channel=T3.channel
ORDER BY `日期` desc,`设备类型`,`活跃类型`,`渠道`
--美购详情页的来源
SELECT T1.partition_date as `日期`
,T1.device_type as `设备类型`
,T1.active_type as `活跃类型`
,T1.channel as `渠道`
,T1.wel_uv as `美购详情页uv`
,T1.search_result_welfare_uv as `搜索结果美购页uv`
,T2.search_result_welfare_uv as `搜索结果美购页-转化uv`
,T3.result_wel_add_uv as `搜索结果美购页-转化点击加车uv`
,T3.result_wel_buy_uv as `搜索结果美购页-转化点击立即支付uv`
,T3.result_wel_msg_uv as `搜索结果美购页-转化点击私信咨询uv`
,concat(round(T2.search_result_welfare_uv/T1.search_result_welfare_uv*100,2),'%') as `搜索结果美购页-转化uv率`
,concat(round(T2.search_result_welfare_uv/T1.wel_uv*100,2),'%') as `搜索结果美购页-转化美购uv占比`
,concat(round(T3.result_wel_add_uv/T2.search_result_welfare_uv*100,2),'%') as `搜索结果美购页-点击加车率`
,concat(round(T3.result_wel_buy_uv/T2.search_result_welfare_uv*100,2),'%') as `搜索结果美购页-点击立即支付率`
,concat(round(T3.result_wel_msg_uv/T2.search_result_welfare_uv*100,2),'%') as `搜索结果美购页-点击私信咨询率`
,T1.organization_detail_uv as `医院主页uv`
,T2.organization_detail_uv as `医院主页-转化uv`
,T3.org_add_uv as `医院主页-转化点击加车uv`
,T3.org_buy_uv as `医院主页-转化点击立即支付uv`
,T3.org_msg_uv as `医院主页-转化点击私信咨询uv`
,concat(round(T2.organization_detail_uv/T1.organization_detail_uv*100,2),'%') as `医院主页-转化uv率`
,concat(round(T2.organization_detail_uv/T1.wel_uv*100,2),'%') as `医院主页-转化美购uv占比`
,concat(round(T3.org_add_uv/T2.organization_detail_uv*100,2),'%') as `医院主页-点击加车率`
,concat(round(T3.org_buy_uv/T2.organization_detail_uv*100,2),'%') as `医院主页-点击立即支付率`
,concat(round(T3.org_msg_uv/T2.organization_detail_uv*100,2),'%') as `医院主页-点击私信咨询率`
,T1.category_uv as `品类聚合页uv`
,T2.category_uv as `品类聚合页-转化uv`
,T3.category_add_uv as `品类聚合页-转化点击加车uv`
,T3.category_buy_uv as `品类聚合页-转化点击立即支付uv`
,T3.category_msg_uv as `品类聚合页-转化点击私信咨询uv`
,concat(round(T2.category_uv/T1.category_uv*100,2),'%') as `品类聚合页-转化uv率`
,concat(round(T2.category_uv/T1.wel_uv*100,2),'%') as `品类聚合页-转化美购uv占比`
,concat(round(T3.category_add_uv/T2.category_uv*100,2),'%') as `品类聚合页-点击加车率`
,concat(round(T3.category_buy_uv/T2.category_uv*100,2),'%') as `品类聚合页-点击立即支付率`
,concat(round(T3.category_msg_uv/T2.category_uv*100,2),'%') as `品类聚合页-点击私信咨询率`
,T1.conversation_detail_uv as `私信详情页uv`
,T2.conversation_detail_uv as `私信详情页-转化uv`
,T3.conv_add_uv as `私信详情页-转化点击加车uv`
,T3.conv_buy_uv as `私信详情页-转化点击立即支付uv`
,T3.conv_msg_uv as `私信详情页-转化点击私信咨询uv`
,concat(round(T2.conversation_detail_uv/T1.conversation_detail_uv*100,2),'%') as `私信详情页-转化uv率`
,concat(round(T2.conversation_detail_uv/T1.wel_uv*100,2),'%') as `私信详情页-转化美购uv占比`
,concat(round(T3.conv_add_uv/T2.conversation_detail_uv*100,2),'%') as `私信详情页-点击加车率`
,concat(round(T3.conv_buy_uv/T2.conversation_detail_uv*100,2),'%') as `私信详情页-点击立即支付率`
,concat(round(T3.conv_msg_uv/T2.conversation_detail_uv*100,2),'%') as `私信详情页-点击私信咨询率`
,T1.welfare_list_uv as `美购列表页uv`
,T2.welfare_list_uv as `美购列表页-转化uv`
,T3.wel_list_add_uv as `美购列表页-转化点击加车uv`
,T3.wel_list_buy_uv as `美购列表页-转化点击立即支付uv`
,T3.wel_list_msg_uv as `美购列表页-转化点击私信咨询uv`
,concat(round(T2.welfare_list_uv/T1.welfare_list_uv*100,2),'%') as `美购列表页-转化uv率`
,concat(round(T2.welfare_list_uv/T1.wel_uv*100,2),'%') as `美购列表页-转化美购uv占比`
,concat(round(T3.wel_list_add_uv/T2.welfare_list_uv*100,2),'%') as `美购列表页-点击加车率`
,concat(round(T3.wel_list_buy_uv/T2.welfare_list_uv*100,2),'%') as `美购列表页-点击立即支付率`
,concat(round(T3.wel_list_msg_uv/T2.welfare_list_uv*100,2),'%') as `美购列表页-点击私信咨询率`
,T1.my_cart_uv as`购物车uv`
,T2.my_cart_uv as`购物车-转化uv`
,T3.cart_add_uv as `购物车-转化点击加车uv`
,T3.cart_buy_uv as `购物车-转化点击立即支付uv`
,T3.cart_msg_uv as `购物车-转化点击私信咨询uv`
,concat(round(T2.my_cart_uv/T1.my_cart_uv*100,2),'%') as `购物车-转化uv率`
,concat(round(T2.my_cart_uv/T1.wel_uv*100,2),'%') as `购物车-转化美购uv占比`
,concat(round(T3.cart_add_uv/T2.my_cart_uv*100,2),'%') as `购物车-点击加车率`
,concat(round(T3.cart_buy_uv/T2.my_cart_uv*100,2),'%') as `购物车-点击立即支付率`
,concat(round(T3.cart_msg_uv/T2.my_cart_uv*100,2),'%') as `购物车-点击私信咨询率`
,T1.search_result_more_uv as `搜索结果综合页uv`
,T2.search_result_more_uv as `搜索结果综合页-转化uv`
,T3.result_more_add_uv as `搜索结果综合页-转化点击加车uv`
,T3.result_more_buy_uv as `搜索结果综合页-转化点击立即支付uv`
,T3.result_more_msg_uv as `搜索结果综合页-转化点击私信咨询uv`
,concat(round(T2.search_result_more_uv/T1.search_result_more_uv*100,2),'%') as `搜索结果综合页-转化uv率`
,concat(round(T2.search_result_more_uv/T1.wel_uv*100,2),'%') as `搜索结果综合页-转化美购uv占比`
,concat(round(T3.result_more_add_uv/T2.search_result_more_uv*100,2),'%') as `搜索结果综合页-点击加车率`
,concat(round(T3.result_more_buy_uv/T2.search_result_more_uv*100,2),'%') as `搜索结果综合页-点击立即支付率`
,concat(round(T3.result_more_msg_uv/T2.search_result_more_uv*100,2),'%') as `搜索结果综合页-点击私信咨询率`
,T1.order_detail_uv as `订单详情页uv`
,T2.order_detail_uv as `订单详情页-转化uv`
,T3.order_add_uv as `订单详情页-转化点击加车uv`
,T3.order_buy_uv as `订单详情页-转化点击立即支付uv`
,T3.order_msg_uv as `订单详情页-转化点击私信咨询uv`
,concat(round(T2.order_detail_uv/T1.order_detail_uv*100,2),'%') as `订单详情页-转化uv率`
,concat(round(T2.order_detail_uv/T1.wel_uv*100,2),'%') as `订单详情页-转化美购uv占比`
,concat(round(T3.order_add_uv/T2.order_detail_uv*100,2),'%') as `订单详情页-点击加车率`
,concat(round(T3.order_buy_uv/T2.order_detail_uv*100,2),'%') as `订单详情页-点击立即支付率`
,concat(round(T3.order_msg_uv/T2.order_detail_uv*100,2),'%') as `订单详情页-点击私信咨询率`
,T1.special_uv as `专题和大促页uv`
,T2.special_uv as `专题和大促页-转化uv`
,T3.special_add_uv as `专题和大促页-转化点击加车uv`
,T3.special_buy_uv as `专题和大促页-转化点击立即支付uv`
,T3.special_msg_uv as `专题和大促页-转化点击私信咨询uv`
,concat(round(T2.special_uv/T1.special_uv*100,2),'%') as `专题和大促页-转化uv率`
,concat(round(T2.special_uv/T1.wel_uv*100,2),'%') as `专题和大促页-转化美购uv占比`
,concat(round(T3.special_add_uv/T2.special_uv*100,2),'%') as `专题和大促页-点击加车率`
,concat(round(T3.special_buy_uv/T2.special_uv*100,2),'%') as `专题和大促页-点击立即支付率`
,concat(round(T3.special_msg_uv/T2.special_uv*100,2),'%') as `专题和大促页-点击私信咨询率`
,T1.expert_detail_uv as `医生主页uv`
,T2.expert_detail_uv as `医生主页-转化uv`
,T3.exp_add_uv as `医生主页-转化点击加车uv`
,T3.exp_buy_uv as `医生主页-转化点击立即支付uv`
,T3.exp_msg_uv as `医生主页-转化点击私信咨询uv`
,concat(round(T2.expert_detail_uv/T1.expert_detail_uv*100,2),'%') as `医生主页-转化uv率`
,concat(round(T2.expert_detail_uv/T1.wel_uv*100,2),'%') as `医生主页-转化美购uv占比`
,concat(round(T3.exp_add_uv/T2.expert_detail_uv*100,2),'%') as `医生主页-点击加车率`
,concat(round(T3.exp_buy_uv/T2.expert_detail_uv*100,2),'%') as `医生主页-点击立即支付率`
,concat(round(T3.exp_msg_uv/T2.expert_detail_uv*100,2),'%') as `医生主页-点击私信咨询率`
,T1.wel_uv as `美购详情页uv`
,T2.wel_uv as `其他美购详情页-转化uv`
,T3.wel_add_uv as `其他美购详情页-转化点击加车uv`
,T3.wel_buy_uv as `其他美购详情页-转化点击立即支付uv`
,T3.wel_msg_uv as `其他美购详情页-转化点击私信咨询uv`
,concat(round(T2.wel_uv/T1.wel_uv*100,2),'%') as `其他美购详情页-转化uv率`
,concat(round(T2.wel_uv/T1.wel_uv*100,2),'%') as `其他美购详情页-转化美购uv占比`
,concat(round(T3.wel_add_uv/T2.wel_uv*100,2),'%') as `其他美购详情页-点击加车率`
,concat(round(T3.wel_buy_uv/T2.wel_uv*100,2),'%') as `其他美购详情页-点击立即支付率`
,concat(round(T3.wel_msg_uv/T2.wel_uv*100,2),'%') as `其他美购详情页-点击私信咨询率`
,T1.welfare_home_uv as `美购首页uv`
,T2.welfare_home_uv as `美购首页-转化uv`
,T3.wel_home_add_uv as `美购首页-转化点击加车uv`
,T3.wel_home_buy_uv as `美购首页-转化点击立即支付uv`
,T3.wel_home_msg_uv as `美购首页-转化点击私信咨询uv`
,concat(round(T2.welfare_home_uv/T1.welfare_home_uv*100,2),'%') as `美购首页-转化uv率`
,concat(round(T2.welfare_home_uv/T1.wel_uv*100,2),'%') as `美购首页-转化美购uv占比`
,concat(round(T3.wel_home_add_uv/T2.welfare_home_uv*100,2),'%') as `美购首页-点击加车率`
,concat(round(T3.wel_home_buy_uv/T2.welfare_home_uv*100,2),'%') as `美购首页-点击立即支付率`
,concat(round(T3.wel_home_msg_uv/T2.welfare_home_uv*100,2),'%') as `美购首页-点击私信咨询率`
,T1.diary_detail_uv as `日记本详情页uv`
,T2.diary_detail_uv as `日记本详情页-转化uv`
,T3.diary_add_uv as `日记本详情页-转化点击加车uv`
,T3.diary_buy_uv as `日记本详情页-转化点击立即支付uv`
,T3.diary_msg_uv as `日记本详情页-转化点击私信咨询uv`
,concat(round(T2.diary_detail_uv/T1.diary_detail_uv*100,2),'%') as `日记本详情页-转化uv率`
,concat(round(T2.diary_detail_uv/T1.wel_uv*100,2),'%') as `日记本详情页-转化美购uv占比`
,concat(round(T3.diary_add_uv/T2.diary_detail_uv*100,2),'%') as `日记本详情页-点击加车率`
,concat(round(T3.diary_buy_uv/T2.diary_detail_uv*100,2),'%') as `日记本详情页-点击立即支付率`
,concat(round(T3.diary_msg_uv/T2.diary_detail_uv*100,2),'%') as `日记本详情页-点击私信咨询率`
,T1.sign_uv as `签到页uv`
,T2.sign_uv as `签到页-转化uv`
,T3.sign_add_uv as `签到页-转化点击加车uv`
,T3.sign_buy_uv as `签到页-转化点击立即支付uv`
,T3.sign_msg_uv as `签到页-转化点击私信咨询uv`
,concat(round(T2.sign_uv/T1.sign_uv*100,2),'%') as `签到页-转化uv率`
,concat(round(T2.sign_uv/T1.wel_uv*100,2),'%') as `签到页-转化美购uv占比`
,concat(round(T3.sign_add_uv/T2.sign_uv*100,2),'%') as `签到页-点击加车率`
,concat(round(T3.sign_buy_uv/T2.sign_uv*100,2),'%') as `签到页-点击立即支付率`
,concat(round(T3.sign_msg_uv/T2.sign_uv*100,2),'%') as `签到页-点击私信咨询率`
,T1.ai_report_uv as `AI结果页uv`
,T2.ai_report_uv as `AI结果页-转化uv`
,T3.ai_add_uv as `AI结果页-转化点击加车uv`
,T3.ai_buy_uv as `AI结果页-转化点击立即支付uv`
,T3.ai_msg_uv as `AI结果页-转化点击私信咨询uv`
,concat(round(T2.ai_report_uv/T1.ai_report_uv*100,2),'%') as `AI结果页-转化uv率`
,concat(round(T2.ai_report_uv/T1.wel_uv*100,2),'%') as `AI结果页-转化美购uv占比`
,concat(round(T3.ai_add_uv/T2.ai_report_uv*100,2),'%') as `AI结果页-点击加车率`
,concat(round(T3.ai_buy_uv/T2.ai_report_uv*100,2),'%') as `AI结果页-点击立即支付率`
,concat(round(T3.ai_msg_uv/T2.ai_report_uv*100,2),'%') as `AI结果页-点击私信咨询率`
,T1.zone_uv as `内容聚合页uv`
,T2.zone_uv as `内容聚合页-转化uv`
,T3.zone_add_uv as `内容聚合页-转化点击加车uv`
,T3.zone_buy_uv as `内容聚合页-转化点击立即支付uv`
,T3.zone_msg_uv as `内容聚合页-转化点击私信咨询uv`
,concat(round(T2.zone_uv/T1.zone_uv*100,2),'%') as `内容聚合页-转化uv率`
,concat(round(T2.zone_uv/T1.wel_uv*100,2),'%') as `内容聚合页-转化美购uv占比`
,concat(round(T3.zone_add_uv/T2.zone_uv*100,2),'%') as `内容聚合页-点击加车率`
,concat(round(T3.zone_buy_uv/T2.zone_uv*100,2),'%') as `内容聚合页-点击立即支付率`
,concat(round(T3.zone_msg_uv/T2.zone_uv*100,2),'%') as `内容聚合页-点击私信咨询率`
FROM
(--能够走向美购详情页的各页面uv/uv
SELECT t1.partition_date
,t1.device_type
,t1.active_type
,t2.channel
,count(case when page_name = 'welfare_detail' then t1.cl_id end) as wel_uv
,count(case when page_name = 'search_result_more' then t1.cl_id end) as search_result_more_uv
,count(case when page_name = 'search_result_welfare' then t1.cl_id end) as search_result_welfare_uv
,count(case when page_name = 'organization_detail' then t1.cl_id end) as organization_detail_uv
,count(case when page_name = 'expert_detail' then t1.cl_id end) as expert_detail_uv
,count(case when page_name = 'category' then t1.cl_id end) as category_uv
,count(case when page_name = 'welfare_list' then t1.cl_id end) as welfare_list_uv
,count(case when page_name = 'welfare_home' then t1.cl_id end) as welfare_home_uv
,count(case when page_name = 'conversation_detail' then t1.cl_id end) as conversation_detail_uv
,count(case when page_name = 'my_cart' then t1.cl_id end) as my_cart_uv
,count(case when page_name = 'diary_detail' then t1.cl_id end) as diary_detail_uv
,count(case when page_name = 'order_detail' then t1.cl_id end) as order_detail_uv
,count(case when page_name ='new_sign' then t1.cl_id end) as sign_uv
,count(case when page_name in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') then t1.cl_id end) as special_uv --专题和大促
,count(case when page_name = 'zone_v3' then t1.cl_id end) as zone_uv
,count(case when page_name in ('report_result','face_detect_result') then t1.cl_id end) as ai_report_uv --待之后增加模拟整形页面
FROM
(
SELECT t1.partition_date,t1.page_name,t1.cl_id,mas.device_type,mas.active_type,mas.channel
FROM
(
SELECT partition_date,page_name,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='page_view'
)t1
JOIN
(
SELECT partition_date,device_os_type as device_type,m.device_id
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20190101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)mas
ON t1.cl_id=mas.device_id
AND t1.partition_date=mas.partition_date
LEFT JOIN
( -- 去掉疑似机构刷量的pV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t1.cl_id=spam_pv.cl_id
WHERE spam_pv.cl_id IS NULL
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY t1.partition_date,t1.device_type,t1.active_type,t2.channel
)T1
LEFT JOIN
(--不同referrer下的美购详情页uv/uv
SELECT t1.partition_date
,t1.device_type
,t1.active_type
,t2.channel
,count(case when referrer = 'welfare_detail' then t1.cl_id end) as wel_uv
,count(case when referrer = 'search_result_more' then t1.cl_id end) as search_result_more_uv
,count(case when referrer = 'search_result_welfare' then t1.cl_id end) as search_result_welfare_uv
,count(case when referrer = 'organization_detail' then t1.cl_id end) as organization_detail_uv
,count(case when referrer = 'expert_detail' then t1.cl_id end) as expert_detail_uv
,count(case when referrer = 'category' then t1.cl_id end) as category_uv
,count(case when referrer = 'welfare_list' then t1.cl_id end) as welfare_list_uv
,count(case when referrer = 'welfare_home' then t1.cl_id end) as welfare_home_uv
,count(case when referrer = 'conversation_detail' then t1.cl_id end) as conversation_detail_uv
,count(case when referrer = 'my_cart' then t1.cl_id end) as my_cart_uv
,count(case when referrer = 'diary_detail' then t1.cl_id end) as diary_detail_uv
,count(case when referrer = 'order_detail' then t1.cl_id end) as order_detail_uv
,count(case when referrer ='new_sign' then t1.cl_id end) as sign_uv
,count(case when referrer in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') then t1.cl_id end) as special_uv --专题和大促
,count(case when referrer = 'zone_v3' then t1.cl_id end) as zone_uv
,count(case when referrer in ('report_result','face_detect_result') then t1.cl_id end) as ai_report_uv --待之后增加模拟整形页面
FROM
(
SELECT t1.partition_date,t1.referrer,t1.cl_id,mas.device_type,mas.active_type,mas.channel
FROM
(
SELECT partition_date,referrer,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='page_view'
)t1
JOIN
(
SELECT partition_date,device_os_type as device_type,m.device_id
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20190101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)mas
ON t1.cl_id=mas.device_id
AND t1.partition_date=mas.partition_date
LEFT JOIN
( -- 去掉疑似机构刷量的pV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t1.cl_id=spam_pv.cl_id
WHERE spam_pv.cl_id IS NULL
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY t1.partition_date,t1.device_type,t1.active_type,t2.channel
)T2
ON T1.partition_date=T2.partition_date
and T1.device_type=T2.device_type
AND T1.active_type=T2.active_type
AND T1.channel=T2.channel
LEFT JOIN
(--点击加车/支付/私信的不同来源
SELECT t1.partition_date
,t1.device_type
,t1.active_type
,t2.channel
,count(case when referrer = 'welfare_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as wel_add_uv
,count(case when referrer = 'welfare_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as wel_buy_uv
,count(case when referrer = 'welfare_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as wel_msg_uv
,count(case when referrer = 'search_result_more' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as result_more_add_uv
,count(case when referrer = 'search_result_more' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as result_more_buy_uv
,count(case when referrer = 'search_result_more' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as result_more_msg_uv
,count(case when referrer = 'search_result_welfare' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as result_wel_add_uv
,count(case when referrer = 'search_result_welfare' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as result_wel_buy_uv
,count(case when referrer = 'search_result_welfare' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as result_wel_msg_uv
,count(case when referrer = 'organization_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as org_add_uv
,count(case when referrer = 'organization_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as org_buy_uv
,count(case when referrer = 'organization_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as org_msg_uv
,count(case when referrer = 'expert_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as exp_add_uv
,count(case when referrer = 'expert_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as exp_buy_uv
,count(case when referrer = 'expert_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as exp_msg_uv
,count(case when referrer = 'category' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as category_add_uv
,count(case when referrer = 'category' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as category_buy_uv
,count(case when referrer = 'category' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as category_msg_uv
,count(case when referrer = 'welfare_list' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as wel_list_add_uv
,count(case when referrer = 'welfare_list' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as wel_list_buy_uv
,count(case when referrer = 'welfare_list' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as wel_list_msg_uv
,count(case when referrer = 'welfare_home' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as wel_home_add_uv
,count(case when referrer = 'welfare_home' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as wel_home_buy_uv
,count(case when referrer = 'welfare_home' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as wel_home_msg_uv
,count(case when referrer = 'conversation_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as conv_add_uv
,count(case when referrer = 'conversation_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as conv_buy_uv
,count(case when referrer = 'conversation_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as conv_msg_uv
,count(case when referrer = 'my_cart' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as cart_add_uv
,count(case when referrer = 'my_cart' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as cart_buy_uv
,count(case when referrer = 'my_cart' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as cart_msg_uv
,count(case when referrer = 'diary_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as diary_add_uv
,count(case when referrer = 'diary_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as diary_buy_uv
,count(case when referrer = 'diary_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as diary_msg_uv
,count(case when referrer = 'order_detail' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as order_add_uv
,count(case when referrer = 'order_detail' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as order_buy_uv
,count(case when referrer = 'order_detail' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as order_msg_uv
,count(case when referrer = 'new_sign' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as sign_add_uv
,count(case when referrer = 'new_sign' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as sign_buy_uv
,count(case when referrer = 'new_sign' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as sign_msg_uv
,count(case when referrer in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as special_add_uv
,count(case when referrer in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as special_buy_uv
,count(case when referrer in ('special_polymer','newt_welfare_special','welfare_special','activity_promotion_seckill','activity_promotion','custom_special') and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as special_msg_uv
,count(case when referrer = 'zone_v3' and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as zone_add_uv
,count(case when referrer = 'zone_v3' and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as zone_buy_uv
,count(case when referrer = 'zone_v3' and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as zone_msg_uv
,count(case when referrer in ('report_result','face_detect_result') and action = 'welfare_multiattribute_click_add' then t1.cl_id end) as ai_add_uv
,count(case when referrer in ('report_result','face_detect_result') and action = 'welfare_multiattribute_click_buy' then t1.cl_id end) as ai_buy_uv
,count(case when referrer in ('report_result','face_detect_result') and action in ('welfare_detail_click_message','on_click_button') then t1.cl_id end) as ai_msg_uv
FROM
(
SELECT t1.partition_date,t1.referrer,t1.action,t1.cl_id,mas.device_type,mas.active_type,mas.channel
FROM
( --点击加车/支付
SELECT partition_date,referrer,action,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action in ('welfare_multiattribute_click_add','welfare_multiattribute_click_buy')
UNION ALL
--点击私信按钮
SELECT partition_date,referrer,action,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >=regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
--AND page_name = 'welfare_detail'
AND action='welfare_detail_click_message'
UNION ALL
--点击私信区域(目前referrer缺失,故通过拆解referrer_link的方式获得)
SELECT partition_date,referrer,action,cl_id
FROM
(
SELECT partition_date,cl_id,action,t2.referrer as referrer
,row_number () over (PARTITION BY t1.referrer_link,t1.cl_id ORDER BY t2.link_id desc) as rank
from
( SELECT partition_date,params['referrer_link'] as referrer_link,cl_id,action
,json_split(params['referrer_link'],'string') as a
FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND page_name = 'welfare_detail'
AND action='on_click_button'
AND params['button_name'] in ('question_tag','appointment')
)t1
lateral view posexplode(a) t2 as link_id,referrer
)t3
where rank=1
)t1
JOIN
(
SELECT partition_date,device_os_type as device_type,m.device_id
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,array(CASE WHEN first_channel_source_type like '%xinyouxingkong%' or a.device_id is not NULL
or first_channel_source_type in ('promotion_aisi','promotion_koomobi_km00','promotion_koomobi_km01')
or first_channel_source_type like '%longyuzhixing%' or first_channel_source_type like '%jingmeng%'
or first_channel_source_type like '%mailuo%' THEN '可疑'
WHEN (partition_date>='20190601' and tmp.col2 = 'AI')
or (partition_date < '20200301' AND partition_date>='20190601' and first_channel_source_type like 'promotion_toutiao_jy%')
or (partition_date>='20200601' and ((first_channel_source_type like 'promotion_toutiao_jy%') or (first_channel_source_type like 'dyand%') or (first_channel_source_type like 'douyin%')))
THEN 'AI' ELSE '其他' END , '合计') as channel
FROM online.ml_device_day_active_status m
LEFT JOIN
(SELECT col1,col2 --col1:子渠道,col2:是否属于AI,col3:标识
FROM pm.tl_pm_ydl
WHERE col3='0204_danlei_channel')tmp
on first_channel_source_type=tmp.col1
LEFT JOIN
(SELECT DISTINCT device_id
FROM al.al_pm_ct_dv_deviceappversionrollbackfrom20190101_d
WHERE partition_day = regexp_replace(DATE_SUB(current_date,2) ,'-',''))a
ON m.device_id = a.device_id
where partition_date >= regexp_replace(DATE_SUB(current_date,90) ,'-','')
AND partition_date < regexp_replace((current_date),'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei','','unknown')
AND first_channel_source_type not like 'promotion\_jf\_%'
)mas
ON t1.cl_id=mas.device_id
AND t1.partition_date=mas.partition_date
LEFT JOIN
( -- 去掉疑似机构刷量的PV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(DATE_SUB(current_date,1) ,'-','')
)spam_pv
on t1.cl_id=spam_pv.cl_id
WHERE spam_pv.cl_id IS NULL
)t1
LATERAL VIEW explode(t1.channel) t2 AS channel
GROUP BY t1.partition_date,t1.device_type,t1.active_type,t2.channel
)T3
ON T1.partition_date=T3.partition_date
and T1.device_type=T3.device_type
AND T1.active_type=T3.active_type
AND T1.channel=T3.channel
ORDER BY `日期` desc,`设备类型`,`活跃类型`,`渠道`
SELECT
day_id AS `日期`
,device_os_type AS `设备类型`
,active_type AS `活跃类型`
,search_entrance AS `搜索入口`
,click_search_pv AS `点击搜索框pv`
,click_search_uv AS `点击搜索框uv`
FROM pm.tl_pm_search_click_path_d
WHERE partition_day>='20200619' and partition_day<=regexp_replace(DATE_SUB(current_date,1) ,'-','')
order by `日期` desc ,`设备类型`,`活跃类型`,`点击搜索框pv`desc
\ No newline at end of file
--近7天搜索方式的搜索量
SELECT regexp_replace(DATE_SUB(current_date,1) ,'-','') AS `日期`,
T4.QUERY AS `搜索词`,
T4.INPUT_TYPE AS `搜索类型`,
T4.SEARCH_PV AS `搜索量`
FROM
(SELECT T3.*
FROM (SELECT T2.*,
SUM(SEARCH_PV_ALL) OVER(PARTITION BY T2.QUERY) SEARCH_PV_SUM,
ROW_NUMBER() OVER(PARTITION BY T2.QUERY ORDER BY SEARCH_PV DESC) SEARCH_PV_GROUP_SUM,
DENSE_RANK() OVER(ORDER BY SUM(SEARCH_PV_ALL) OVER(PARTITION BY T2.QUERY) DESC,T2.QUERY) SEARCH_PV_GROUP
FROM (SELECT T1.*,
CASE
WHEN INPUT_TYPE = '全部' THEN
0
ELSE
1
END INPUT_TYPE_RANK,
CASE
WHEN INPUT_TYPE = '全部' THEN
SEARCH_PV
ELSE
0
END SEARCH_PV_ALL
FROM (SELECT QUERY,INPUT_TYPE,SUM(SEARCH_PV) AS SEARCH_PV
FROM PM.TL_PM_SEARCH_INPUT_TYPE_D T
WHERE T.PARTITION_DAY >= regexp_replace(DATE_SUB(current_date,7) ,'-','')
AND T.PARTITION_DAY<regexp_replace((current_date),'-','')
AND T.DAY_ID >= regexp_replace(DATE_SUB(current_date,7) ,'-','')
AND T.DAY_ID<regexp_replace((current_date),'-','')
GROUP BY T.QUERY,T.INPUT_TYPE) T1) T2)T3
WHERE SEARCH_PV_GROUP<=300
ORDER BY T3.SEARCH_PV_SUM DESC,
T3.QUERY,
T3.INPUT_TYPE_RANK,
T3.SEARCH_PV_GROUP_SUM)T4
\ No newline at end of file
SELECT
day_id AS `日期`
,query AS `关键词`
,search_pv AS `搜索量`
,search_uv AS `搜索uv`
,NVL(case when NVL(page_more_pv,0)>0 then concat(round(more_click_pv*100/page_more_pv,2) ,'%') else 0 end, 0) as `搜索综合结果页内容卡片点击PV/搜索综合结果页浏览pv`
,NVL(case when NVL(page_more_pv,0)>0 then concat(round(more_click_10_pv*100/page_more_pv,2) ,'%') else 0 end,0) as `搜索综合结果页前10内容卡片点击PV/搜索综合结果页浏览pv`
,NVL(case when NVL(page_more_pv,0)>0 then concat(round(more_click_5_diary_pv*100/page_more_pv,2),'%') else 0 end,0) as `搜索综合结果页前5日记卡片点击PV/搜索综合结果页浏览pv`
,NVL(case when NVL(page_more_pv,0)>0 then concat(round(more_click_5_answer_pv*100/page_more_pv,2),'%') else 0 end,0) as `搜索综合结果页前5问答卡片点击PV/搜索综合结果页浏览pv`
,NVL(case when NVL(page_more_pv,0)>0 then concat(round(more_click_5_topic_pv*100/page_more_pv,2),'%') else 0 end,0) as `搜索综合结果页前5帖子卡片点击PV/搜索综合结果页浏览pv`
,NVL(case when NVL(page_wel_pv,0)>0 then concat(round(wel_click_pv*100/page_wel_pv,2),'%') else 0 end,0) as `搜索美购结果页卡片点击PV/搜索美购结果页pv`
,NVL(case when NVL(page_wel_pv,0)>0 then concat(round(wel_click_10_pv*100/page_wel_pv,2),'%') else 0 end,0) as `搜索美购结果页前10卡片点击PV/搜索美购结果页pv`
,NVL(case when NVL(page_wel_pv,0)>0 then concat(round(wel_click_5_pv*100/page_wel_pv,2),'%') else 0 end,0) as `搜索美购结果页前5卡片点击PV/搜索美购结果页pv`
,NVL(case when NVL(page_diary_pv,0)>0 then concat(round(diary_click_pv*100/page_diary_pv,2),'%') else 0 end,0) as `搜索日记结果页卡片点击PV/搜索日记结果页pv`
,NVL(case when NVL(page_diary_pv,0)>0 then concat(round(diary_click_10_pv*100/page_diary_pv,2),'%') else 0 end,0) as `搜索日记结果页前10卡片点击PV/搜索日记结果页pv`
,NVL(case when NVL(page_diary_pv,0)>0 then concat(round(diary_click_5_pv*100/page_diary_pv,2),'%') else 0 end,0) as `搜索日记结果页前5卡片点击PV/搜索日记结果页pv`
,search_more_pv AS `综合tab下的搜索的点击pv`
,page_more_pv AS `搜索综合结果页浏览PV`
,more_click_pv AS `搜索综合结果页内容卡片点击PV`
,more_click_10_pv AS `搜索综合结果页前10内容卡片点击PV`
,more_click_5_diary_pv AS `搜索综合结果页前5日记卡片点击PV`
,more_click_5_answer_pv AS `搜索综合结果页前5问答卡片点击PV`
,more_click_5_topic_pv AS `搜索综合结果页前5帖子卡片点击PV`
,search_wel_pv AS `美购tab下的搜索的点击pv`
,page_wel_pv AS `搜索美购结果页浏览pv`
,wel_click_pv AS `搜索美购结果页卡片点击PV`
,wel_click_10_pv AS `搜索美购结果页前10卡片点击PV`
,wel_click_5_pv AS `搜索美购结果页前5卡片点击PV`
,search_diary_pv AS `日记tab下的搜索的点击pv`
,page_diary_pv AS `搜索日记结果页浏览pv`
,diary_click_pv AS `搜索日记结果页卡片点击PV`
,diary_click_10_pv AS `搜索日记结果页前10卡片点击PV`
,diary_click_5_pv AS `搜索日记结果页前5卡片点击PV`
FROM pm.tl_pm_search_result_click_rate_d
WHERE partition_day>='20200619' and partition_day<=regexp_replace(DATE_SUB(current_date,1) ,'-','')
and day_id>=regexp_replace(DATE_SUB(current_date,7) ,'-','')
and day_id<=regexp_replace(DATE_SUB(current_date,1) ,'-','')
order by `日期` desc,`搜索量` desc,`关键词`
SET mapreduce.job.queuename=data;
SET mapreduce.map.memory.mb=8192;
SET mapreduce.map.java.opts=-Xmx8000m;
SET mapreduce.reduce.memory.mb=8192;
SET mapreduce.reduce.java.opts=-Xmx8000m;
set hive.auto.convert.join=true;
SET mapred.reduce.tasks=20;
SET role admin;
INSERT OVERWRITE TABLE pm.tl_pm_search_click_path_d PARTITION (PARTITION_DAY = ${partition_day})
SELECT day_id as day_id
,device_os_type as device_os_type
,active_type as active_type
,v.search_entrance as search_entrance
,sum(search_pv) as click_search_pv
,sum(search_uv) as click_search_uv
FROM
(
SELECT day_id,device_os_type,active_type,array(search_entrance,'合计') as search_entrance
,search_pv,search_uv
FROM
(
SELECT t1.partition_date as day_id
,t1.device_os_type
,t1.active_type
,case when action='on_click_navbar_search' and page_name='home' then '首页搜索框'
when action='on_click_navbar_search' and page_name='welfare_home' then '美购首页搜索框'
when action='on_click_navbar_search' and page_name='category' then '品类聚合页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["home","category"]' then '来自品类聚合的美购列表页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["welfare_home"]' then '来自美购首页的美购列表页搜索框'
when action in ('do_search','on_click_navbar_search')
and page_name in ('diary_detail','topic_detail','post_detail','user_post_detail'
,'doctor_post_detail','question_detail','answer_detail','question_answer_detail') then '内容详情页搜索框'
when action ='详情页高亮词' then '详情页高亮词搜索'
when action='大家都在看' then '首页feed大家都在看'
when action='热搜词' then '美购首页热搜词' else null end as search_entrance
,count(cl_id) as search_pv
,count(distinct cl_id) as search_uv
FROM
(
SELECT partition_date,device_os_type
,case WHEN active_type = '4' THEN '老活跃设备'
WHEN active_type in ('1','2') then '新增设备' END as active_type
,device_id
FROM online.ml_device_day_active_status
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND active_type in ('1','2','4')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t1
join
(
SELECT partition_date,cl_id,page_name,action,params['referrer_link'] as referrer_link
FROM online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and action in ('do_search','on_click_navbar_search')
union all
SELECT partition_date,cl_id,null as page_name,'大家都在看' as action, null as referrer_link
FROM online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND params['in_page_pos']='猜你喜欢'
AND params['tab_name']='精选'
AND params['card_type']='search_word'
--AND page_name='home' android的page_name为空
union all
SELECT partition_date,cl_id,page_name,'热搜词' as action, null as referrer_link
FROM online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND page_name='welfare_home'
AND params['card_type'] ='search_word'
AND params['in_page_pos']='大家都在搜'
union all
select partition_date,cl_id,null as page_name,'详情页高亮词' as action,null as referrer_link
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and action='on_click_card'
and params['card_type']='highlight_word'
)t2
on t1.partition_date=t2.partition_date and t1.device_id=t2.cl_id
group by t1.partition_date
,t1.device_os_type
,t1.active_type
,case when action='on_click_navbar_search' and page_name='home' then '首页搜索框'
when action='on_click_navbar_search' and page_name='welfare_home' then '美购首页搜索框'
when action='on_click_navbar_search' and page_name='category' then '品类聚合页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["home","category"]' then '来自品类聚合的美购列表页搜索框'
when action='on_click_navbar_search' and page_name='welfare_list' and referrer_link ='["welfare_home"]' then '来自美购首页的美购列表页搜索框'
when action in ('do_search','on_click_navbar_search')
and page_name in ('diary_detail','topic_detail','post_detail','user_post_detail'
,'doctor_post_detail','question_detail','answer_detail','question_answer_detail') then '内容详情页搜索框'
when action ='详情页高亮词' then '详情页高亮词搜索'
when action='大家都在看' then '首页feed大家都在看'
when action='热搜词' then '美购首页热搜词' else null end
having search_entrance is not null
)t
)n
LATERAL VIEW explode(n.search_entrance) v AS search_entrance
group by day_id,device_os_type,active_type,v.search_entrance;
INSERT OVERWRITE TABLE pm.tl_pm_search_input_type_d PARTITION (PARTITION_DAY = ${partition_day})
SELECT partition_date as day_id
,t1.query
,t2.input_type
,sum(t1.all_search_pv) as search_pv
FROM
(
SELECT
partition_date
,query
,array(case when input_type in ('联想','聚合模块') then 'sug点击' else input_type end,'全部') as input_type
,count(click.cl_id) as all_search_pv
,count(distinct click.cl_id) as all_search_uv
FROM
(
SELECT cl_id
,partition_date
,case when params['input_type'] in ('热门','related_search') then '发现' else params['input_type'] end as input_type
,params['query'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action in ('do_search','search_result_click_search')
union all
SELECT cl_id
,partition_date
,'首页精选大家都在看' as input_type
,params['card_name'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND params['in_page_pos']='猜你喜欢'
AND params['tab_name']='精选'
AND params['card_type']='search_word'
--AND page_name='home' android的page_name为空
union all
SELECT cl_id
,partition_date
,'美购首页热搜词' as input_type
,params['card_name'] as query
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_card'
AND page_name='welfare_home'
AND params['card_type'] ='search_word'
AND params['in_page_pos']='大家都在搜'
union all
select cl_id
,partition_date
,'详情页高亮词' as input_type
,params['card_name'] as query
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and int(split(app_version,'\\.')[1]) >= 27
and action='on_click_card'
and params['card_type']='highlight_word'
)click
JOIN
(
SELECT device_id
from online.ml_device_history_detail
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not like 'promotion\_jf\_%'
)dev_channel
on dev_channel.device_id = click.cl_id
GROUP BY partition_date,query,case when input_type in ('联想','聚合模块') then 'sug点击' else input_type end
)t1
LATERAL VIEW explode(t1.input_type) t2 AS input_type
GROUP BY t1.partition_date,t1.query,t2.input_type;
INSERT OVERWRITE TABLE pm.tl_pm_search_result_click_rate_d PARTITION (PARTITION_DAY = ${partition_day})
--搜索关键词日报,取近7天数据,每天取关键词搜索量前500
select t1.partition_date as day_id
,t1.query as query
,NVL(t1.search_pv,0) as search_pv
,NVL(t1.search_uv,0) as search_uv
,NVL(t2.search_more_pv,0) as search_more_pv
,NVL(t2.page_more_pv,0) as page_more_pv
,NVL(t2.more_click_pv,0) as more_click_pv
,NVL(t2.more_click_10_pv,0) as more_click_10_pv
,NVL(t2.more_click_5_diary_pv,0) as more_click_5_diary_pv
,NVL(t2.more_click_5_answer_pv,0) as more_click_5_answer_pv
,NVL(t2.more_click_5_topic_pv,0) as more_click_5_topic_pv
,NVL(t2.search_wel_pv,0) as search_wel_pv
,NVL(t2.page_wel_pv,0) as page_wel_pv
,NVL(t2.wel_click_pv,0) as wel_click_pv
,NVL(t2.wel_click_10_pv,0) as wel_click_10_pv
,NVL(t2.wel_click_5_pv,0) as wel_click_5_pv
,NVL(t2.search_diary_pv,0) as search_diary_pv
,NVL(t2.page_diary_pv,0) as page_diary_pv
,NVL(t2.diary_click_pv,0) as diary_click_pv
,NVL(t2.diary_click_10_pv,0) as diary_click_10_pv
,NVL(t2.diary_click_5_pv,0) as diary_click_5_pv
,NVL(t2.search_more_uv,0) as search_more_uv
,NVL(t2.page_more_uv,0) as page_more_uv
,NVL(t2.more_click_uv,0) as more_click_uv
,NVL(t2.more_click_10_uv,0) as more_click_10_uv
,NVL(t2.more_click_5_diary_uv,0) as more_click_5_diary_uv
,NVL(t2.more_click_5_answer_uv,0) as more_click_5_answer_uv
,NVL(t2.more_click_5_topic_uv,0) as more_click_5_topic_uv
,NVL(t2.search_wel_uv,0) as search_wel_uv
,NVL(t2.page_wel_uv,0) as page_wel_uv
,NVL(t2.wel_click_uv,0) as wel_click_uv
,NVL(t2.wel_click_10_uv,0) as wel_click_10_uv
,NVL(t2.wel_click_5_uv,0) as wel_click_5_uv
,NVL(t2.search_diary_uv,0) as search_diary_uv
,NVL(t2.page_diary_uv,0) as page_diary_uv
,NVL(t2.diary_click_uv,0) as diary_click_uv
,NVL(t2.diary_click_10_uv,0) as diary_click_10_uv
,NVL(t2.diary_click_5_uv,0) as diary_click_5_uv
from
(--总搜索量
select partition_date
,query
,search_pv
,search_uv
from
(
select t1.partition_date
,query
,count(t1.cl_id) as search_pv
,count(distinct t1.cl_id) as search_uv
,row_number() over(partition by partition_date order by count(t1.cl_id) desc) as rank
from
(
select partition_date
,params['query'] as query
,cl_id
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and action in ('do_search','search_result_click_search')
union all
SELECT partition_date
,params['card_name'] as query
,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(date_sub(current_date,1),'-','')
AND action = 'on_click_card'
AND params['in_page_pos']='猜你喜欢'
AND params['tab_name']='精选'
AND params['card_type']='search_word'
--AND page_name='home' android的page_name为空
union all
SELECT partition_date
,params['card_name'] as query
,cl_id
FROM online.bl_hdfs_maidian_updates
WHERE partition_date = regexp_replace(date_sub(current_date,1),'-','')
AND action = 'on_click_card'
AND page_name='welfare_home'
AND params['card_type'] ='search_word'
AND params['in_page_pos']='大家都在搜'
union all
select partition_date
,params['card_name'] as query
,cl_id
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and int(split(app_version,'\\.')[1]) >= 27
and action='on_click_card'
and params['card_type']='highlight_word'
)t1
join
(
SELECT device_id
from online.ml_device_history_detail
WHERE partition_date = regexp_replace(date_sub(current_date,1),'-','')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not like 'promotion\_jf\_%'
)t2
on t1.cl_id=t2.device_id
group by t1.partition_date,query
)t
where rank<=300
)t1
left join
--综合、美购、日记页面浏览pv
(
select t1.partition_date,t1.query
,sum(case when tab_name='综合' then t1.pv end) as search_more_pv
,count(distinct case when tab_name='综合' then t1.cl_id end) as search_more_uv
,sum(case when tab_name='美购' then t1.pv end) as search_wel_pv
,count(distinct case when tab_name='美购' then t1.cl_id end) as search_wel_uv
,sum(case when tab_name='日记' then t1.pv end) as search_diary_pv
,count(distinct case when tab_name='日记' then t1.cl_id end) as search_diary_uv
,sum(case when t2.page_name='综合' then t2.pv end) as page_more_pv
,count(distinct case when t2.page_name='综合' then t2.cl_id end) as page_more_uv
,sum(case when t2.page_name='美购' then t2.pv end) as page_wel_pv
,count(distinct case when t2.page_name='美购' then t2.cl_id end) as page_wel_uv
,sum(case when t2.page_name='日记' then t2.pv end) as page_diary_pv
,count(distinct case when t2.page_name='日记' then t2.cl_id end) as page_diary_uv
,sum(case when t3.page_name='综合' then t3.pv end) as more_click_pv
,count(distinct case when t3.page_name='综合' then t3.cl_id end) as more_click_uv
,sum(case when t3.page_name='美购' then t3.pv end) as wel_click_pv
,count(distinct case when t3.page_name='美购' then t3.cl_id end) as wel_click_uv
,sum(case when t3.page_name='日记' then t3.pv end) as diary_click_pv
,count(distinct case when t3.page_name='日记' then t3.cl_id end) as diary_click_uv
,sum(case when t4.page_name='综合' then t4.pv end) as more_click_10_pv
,count(distinct case when t4.page_name='综合' then t4.cl_id end) as more_click_10_uv
,sum(case when t4.page_name='美购' then t4.pv end) as wel_click_10_pv
,count(distinct case when t4.page_name='美购' then t4.cl_id end) as wel_click_10_uv
,sum(case when t4.page_name='日记' then t4.pv end) as diary_click_10_pv
,count(distinct case when t4.page_name='日记' then t4.cl_id end) as diary_click_10_uv
,sum(case when t5.page_name='美购' then t5.pv end) as wel_click_5_pv
,count(distinct case when t5.page_name='美购' then t5.cl_id end) as wel_click_5_uv
,sum(case when t5.page_name='日记' then t5.pv end) as diary_click_5_pv
,count(distinct case when t5.page_name='日记' then t5.cl_id end) as diary_click_5_uv
,sum(case when t6.page_name='综合' then t6.pv end) as more_click_5_diary_pv
,count(distinct case when t6.page_name='综合' then t6.cl_id end) as more_click_5_diary_uv
,sum(case when t7.page_name='综合' then t7.pv end) as more_click_5_answer_pv
,count(distinct case when t7.page_name='综合' then t7.cl_id end) as more_click_5_answer_uv
,sum(case when t8.page_name='综合' then t8.pv end) as more_click_5_topic_pv
,count(distinct case when t8.page_name='综合' then t8.cl_id end) as more_click_5_topic_uv
from
(--各tab搜索
select partition_date
,params['query'] as query
,cl_id
,params['tab'] as tab_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and params['tab'] in ('综合','美购','日记')
and action in ('search_result_click_tab','search_result_click_search')
group by partition_date,params['query'],cl_id,params['tab']
)t1
left join
(--结果页浏览
select partition_date
,get_json_object(params['extra_param'],'$.query') as query
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end as page_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name in ('search_result_more','search_result_welfare','search_result_diary')
and action ='page_view'
group by partition_date
,get_json_object(params['extra_param'],'$.query')
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end
)t2
on t1.partition_date=t2.partition_date
and t1.query=t2.query
and t1.cl_id=t2.cl_id
and t1.tab_name=t2.page_name
left join
(--内容卡片点击
select partition_date
,params['query'] as query
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end as page_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and action in ('search_result_click_infomation_item','on_click_topic_card','on_click_diary_card','search_result_welfare_click_item')
and page_name in ('search_result_more','search_result_welfare','search_result_diary')
group by partition_date
,params['query']
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end
)t3
on t2.partition_date=t3.partition_date
and t2.query=t3.query
and t2.cl_id=t3.cl_id
and t2.page_name=t3.page_name
left join
(--前10内容卡片点击
select partition_date
,params['query'] as query
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end as page_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and action in ('search_result_click_infomation_item','on_click_topic_card','on_click_diary_card','search_result_welfare_click_item')
and params['position'] in (0,1,2,3,4,5,6,7,8,9)
and page_name in ('search_result_more','search_result_welfare','search_result_diary')
group by partition_date
,params['query']
,cl_id
,case when page_name='search_result_more' then '综合'
when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end
)t4
on t2.partition_date=t4.partition_date
and t2.query=t4.query
and t2.cl_id=t4.cl_id
and t2.page_name=t4.page_name
left join
(--日记、美购前5内容卡片点击
select partition_date
,params['query'] as query
,cl_id
,case when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end as page_name
,count(1) as pv
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and ( action = 'on_click_diary_card' and page_name='search_result_diary'
or action ='search_result_welfare_click_item' and page_name='search_result_welfare')
and params['position'] in (0,1,2,3,4)
group by partition_date
,params['query']
,cl_id
,case when page_name='search_result_welfare' then '美购'
when page_name='search_result_diary' then '日记' end
)t5
on t2.partition_date=t5.partition_date
and t2.query=t5.query
and t2.cl_id=t5.cl_id
and t2.page_name=t5.page_name
left join
(--综搜页日记卡片前5
select c.partition_date,c.query,c.cl_id,'综合' as page_name,count(1) as pv
from
(
SELECT partition_date,query,position
FROM
(
select partition_date
,params['query'] as query
,cast(absolute_position as int) as position
,row_number() over(partition by params['query'], partition_date order by cast (absolute_position as int) asc) as rank
from online.ml_community_precise_exposure_detail
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
and is_exposure = '1' ----精准曝光
and card_content_type='diary'
group by partition_date,params['query'],cast(absolute_position as int)
)a
where rank<=5
)b
join
(
select partition_date
,params['query'] as query
,cl_id
,params['position'] as position
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and (action ='search_result_click_infomation_item'and params['business_type']in('diary','0')
or action ='on_click_diary_card')
)c
on b.partition_date=c.partition_date
and b.query=c.query
and b.position=c.position
group by c.partition_date,c.query,c.cl_id
)t6
on t2.partition_date=t6.partition_date
and t2.query=t6.query
and t2.cl_id=t6.cl_id
and t2.page_name=t6.page_name
left join
(--综搜页回答卡片前5
select c.partition_date,c.query,c.cl_id,'综合' as page_name,count(1) as pv
from
(
SELECT partition_date,query,position
FROM
(
select partition_date
,params['query'] as query
,cast(absolute_position as int) as position
,row_number() over(partition by params['query'], partition_date order by cast (absolute_position as int) asc) as rank
from online.ml_community_precise_exposure_detail
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
and is_exposure = '1' ----精准曝光
and card_content_type='answer'
group by partition_date,params['query'],cast(absolute_position as int)
)a
where rank<=5
)b
join
(
select partition_date
,params['query'] as query
,cl_id
,params['position'] as position
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and action ='search_result_click_infomation_item'
and params['business_type']in ('answer','5')
)c
on b.partition_date=c.partition_date
and b.query=c.query
and b.position=c.position
group by c.partition_date,c.query,c.cl_id
)t7
on t2.partition_date=t7.partition_date
and t2.query=t7.query
and t2.cl_id=t7.cl_id
and t2.page_name=t7.page_name
left join
(--综搜页帖子卡片前5
select c.partition_date,c.query,c.cl_id,'综合' as page_name,count(1) as pv
from
(
SELECT partition_date,query,position
FROM
(
select partition_date
,params['query'] as query
,cast(absolute_position as int) as position
,row_number() over(partition by params['query'], partition_date order by cast (absolute_position as int) asc) as rank
from online.ml_community_precise_exposure_detail
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
and is_exposure = '1' ----精准曝光
and card_content_type='user_post'
group by partition_date,params['query'],cast(absolute_position as int)
)a
where rank<=5
)b
join
(
select partition_date
,params['query'] as query
,cl_id
,params['position'] as position
from online.bl_hdfs_maidian_updates
where partition_date = regexp_replace(date_sub(current_date,1),'-','')
and page_name='search_result_more'
and (action ='search_result_click_infomation_item' and params['business_type'] in ('post','user_post','doctor_post','11')
or action='on_click_topic_card')
)c
on b.partition_date=c.partition_date
and b.query=c.query
and b.position=c.position
group by c.partition_date,c.query,c.cl_id
)t8
on t2.partition_date=t8.partition_date
and t2.query=t8.query
and t2.cl_id=t8.cl_id
and t2.page_name=t8.page_name
join
(
select device_id
from online.ml_device_history_detail
WHERE partition_date = regexp_replace(date_sub(current_date,1),'-','')
and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
,'promotion_shike','promotion_julang_jl03','promotion_zuimei')
AND first_channel_source_type not like 'promotion\_jf\_%'
)dev
on t1.cl_id=dev.device_id
left join
( -- 去掉疑似机构刷量的PV和UV
SELECT distinct device_id
FROM ml.ml_d_ct_dv_devicespam_d
WHERE partition_day=regexp_replace(date_sub(current_date,1),'-','')
)spam_pv
on t2.cl_id=spam_pv.device_id
WHERE spam_pv.device_id IS NULL
group by t1.partition_date,t1.query
)t2
on t1.partition_date=t2.partition_date
and t1.query=t2.query
order by day_id desc,search_pv desc,query;
\ No newline at end of file
--***************************************************************
--*脚本名称: create_pm_c_op_co_content_dimen_d.sql
--*功能: 内容日报
--*业务名称: pm
--*输入数据:
--*作者: weiyimin@igengmei.com
--*更新时间: 2020-5-25 11:00
--***************************************************************
--设置全局变量&UDF
SET mapreduce.job.queuename=data;
--使用bl数据库
USE pm;
--创建BL层内部表
CREATE TABLE IF NOT EXISTS pm.tl_pm_content_d
(
day_id string comment '{"chs_name":"当天日期","description":"","etl":"","value":"","remark":""}',
device_os_type string comment '{"chs_name":"设备类型","description":"","etl":"","value":"","remark":""}',
active_type string comment '{"chs_name":"活跃类型","description":"","etl":"","value":"","remark":""}',
is_ai_channel string comment '{"chs_name":"是否AI渠道","description":"","etl":"","value":"","remark":""}',
dau int comment '{"chs_name":"DAU","description":"","etl":"","value":"","remark":""}',
content_uv int comment '{"chs_name":"内容详情页uv","description":"","etl":"","value":"","remark":""}',
content_pv int comment '{"chs_name":"内容详情页PV","description":"","etl":"","value":"","remark":""}',
per_content_uv string comment '{"chs_name":"内容详情页uv/dau","description":"","etl":"","value":"","remark":""}',
per_content_pv string comment '{"chs_name":"内容详情页pv/dau","description":"","etl":"","value":"","remark":""}',
retention_1 string comment '{"chs_name":"内容用户APP次留","description":"","etl":"","value":"","remark":""}',
retention_7 string comment '{"chs_name":"内容用户APP7留","description":"","etl":"","value":"","remark":""}',
retention_30 string comment '{"chs_name":"内容用户APP30留","description":"","etl":"","value":"","remark":""}',
avg_app_duration double comment '{"chs_name":"内容用户单设备App时长(m)","description":"","etl":"","value":"","remark":""}',
avg_content_stay double comment '{"chs_name":"内容用户单设备内容时长(m)","description":"","etl":"","value":"","remark":""}',
avg_open_times double comment '{"chs_name":"内容用户单设备打开次数","description":"","etl":"","value":"","remark":""}',
search_related_stay double comment '{"chs_name":"内容用户搜索相关页面单设备页面时长(m)","description":"","etl":"","value":"","remark":""}',
welfare_stay double comment '{"chs_name":"内容用户美购详情页单设备页面时长(m)","description":"","etl":"","value":"","remark":""}',
content_question_stay double comment '{"chs_name":"内容用户问题详情页单设备页面时长(m)","description":"","etl":"","value":"","remark":""}',
ai_related_stay double comment '{"chs_name":"内容用户AI相关页面单设备页面时长(m)","description":"","etl":"","value":"","remark":""}',
content_diary_stay double comment '{"chs_name":"内容用户日记详情页单设备页面时长(m)","description":"","etl":"","value":"","remark":""}',
home_stay double comment '{"chs_name":"内容用户首页单设备页面时长(m)","description":"","etl":"","value":"","remark":""}',
conv_related_stay double comment '{"chs_name":"内容用户咨询相关页面单设备页面时长(m)","description":"","etl":"","value":"","remark":""}',
recommend_rate double comment '{"chs_name":"首页feeds推荐进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_recommend_pv double comment '{"chs_name":"首页feeds推荐进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
feeds_rate double comment '{"chs_name":"首页feeds非推荐进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_feeds_pv double comment '{"chs_name":"首页feeds非推荐进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
search_rate double comment '{"chs_name":"搜索进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_search_pv double comment '{"chs_name":"搜索进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
zone_rate double comment '{"chs_name":"内容聚合页进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_zone_pv double comment '{"chs_name":"内容聚合页进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
content_rate double comment '{"chs_name":"内容详情页推荐板块进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_from_content_pv double comment '{"chs_name":"内容详情页推荐板块进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
blank_rate double comment '{"chs_name":"无来源页面(大多数为push)进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_blank_pv double comment '{"chs_name":"无来源页面(大多数为push)进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
comment_rate double comment '{"chs_name":"评论列表页进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_comment_pv double comment '{"chs_name":"评论列表页进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
org_rate double comment '{"chs_name":"医生医院主页进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_org_pv double comment '{"chs_name":"医生医院主页进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
category_rate double comment '{"chs_name":"品类聚合页进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_category_pv double comment '{"chs_name":"品类聚合页进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
my_diary_rate double comment '{"chs_name":"我的日记页进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_my_diary_pv double comment '{"chs_name":"我的日记页进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
ai_rate double comment '{"chs_name":"AI报告页进入内容UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_ai_pv double comment '{"chs_name":"AI报告页进入内容PV/UV","description":"","etl":"","value":"","remark":""}',
create_topic_num int comment '{"chs_name":"真实发帖数","description":"","etl":"","value":"","remark":""}',
create_reply_num int comment '{"chs_name":"真实评论数","description":"","etl":"","value":"","remark":""}',
diary_uv int comment '{"chs_name":"日记UV","description":"","etl":"","value":"","remark":""}',
diary_pv int comment '{"chs_name":"日记PV","description":"","etl":"","value":"","remark":""}',
diary_rate double comment '{"chs_name":"日记UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_diary_pv double comment '{"chs_name":"日记PV/日记UV","description":"","etl":"","value":"","remark":""}',
diary_stay double comment '{"chs_name":"日记单设备时长(m)","description":"","etl":"","value":"","remark":""}',
post_uv int comment '{"chs_name":"帖子UV","description":"","etl":"","value":"","remark":""}',
post_pv int comment '{"chs_name":"帖子PV","description":"","etl":"","value":"","remark":""}',
post_rate double comment '{"chs_name":"帖子UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_post_pv double comment '{"chs_name":"帖子PV/帖子UV","description":"","etl":"","value":"","remark":""}',
post_stay double comment '{"chs_name":"帖子单设备时长(m)","description":"","etl":"","value":"","remark":""}',
question_uv int comment '{"chs_name":"问题UV","description":"","etl":"","value":"","remark":""}',
question_pv int comment '{"chs_name":"问题PV","description":"","etl":"","value":"","remark":""}',
question_rate double comment '{"chs_name":"问题UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_question_pv double comment '{"chs_name":"问题PV/问题UV","description":"","etl":"","value":"","remark":""}',
question_stay double comment '{"chs_name":"问题单设备时长(m)","description":"","etl":"","value":"","remark":""}',
question_answer_uv int comment '{"chs_name":"问答UV","description":"","etl":"","value":"","remark":""}',
question_answer_pv int comment '{"chs_name":"问答PV","description":"","etl":"","value":"","remark":""}',
question_answer_rate double comment '{"chs_name":"问答UV/问答UV","description":"","etl":"","value":"","remark":""}',
per_question_answer_pv double comment '{"chs_name":"问答PV/问答UV","description":"","etl":"","value":"","remark":""}',
question_answer_stay double comment '{"chs_name":"问答单设备时长(m)","description":"","etl":"","value":"","remark":""}',
answer_uv int comment '{"chs_name":"回答UV","description":"","etl":"","value":"","remark":""}',
answer_pv int comment '{"chs_name":"回答PV","description":"","etl":"","value":"","remark":""}',
answer_rate double comment '{"chs_name":"回答UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_answer_pv double comment '{"chs_name":"回答PV/回答UV","description":"","etl":"","value":"","remark":""}',
answer_stay double comment '{"chs_name":"回答单设备时长(m)","description":"","etl":"","value":"","remark":""}',
video_uv int comment '{"chs_name":"视频UV","description":"","etl":"","value":"","remark":""}',
video_pv int comment '{"chs_name":"视频PV","description":"","etl":"","value":"","remark":""}',
video_rate double comment '{"chs_name":"视频UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_video_pv double comment '{"chs_name":"视频PV/视频UV","description":"","etl":"","value":"","remark":""}',
video_stay double comment '{"chs_name":"视频单设备时长(m)","description":"","etl":"","value":"","remark":""}',
wiki_uv int comment '{"chs_name":"百科UV","description":"","etl":"","value":"","remark":""}',
wiki_pv int comment '{"chs_name":"百科PV","description":"","etl":"","value":"","remark":""}',
wiki_rate double comment '{"chs_name":"百科UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_wiki_pv double comment '{"chs_name":"百科PV/百科UV","description":"","etl":"","value":"","remark":""}',
wiki_stay double comment '{"chs_name":"百科单设备时长(m)","description":"","etl":"","value":"","remark":""}',
article_uv int comment '{"chs_name":"专栏UV","description":"","etl":"","value":"","remark":""}',
article_pv int comment '{"chs_name":"专栏PV","description":"","etl":"","value":"","remark":""}',
article_rate double comment '{"chs_name":"专栏UV/内容UV","description":"","etl":"","value":"","remark":""}',
per_article_pv double comment '{"chs_name":"专栏PV/专栏UV","description":"","etl":"","value":"","remark":""}',
article_stay double comment '{"chs_name":"专栏单设备时长(m)","description":"","etl":"","value":"","remark":""}'
)comment '内容日报'
PARTITIONED BY (PARTITION_DAY STRING comment '分区日期')
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
COLLECTION ITEMS TERMINATED BY '\002'
MAP KEYS TERMINATED BY '\003'
LINES TERMINATED BY '\n'
STORED AS TEXTFILE;
\ No newline at end of file
--***************************************************************
--*脚本名称: create_pm_c_op_co_content_dimen_d.sql
--*功能: 内容日报
--*业务名称: pm
--*输入数据:
--*作者: weiyimin@igengmei.com
--*更新时间: 2020-5-25 11:00
--***************************************************************
--设置全局变量&UDF
SET mapreduce.job.queuename=data;
--使用bl数据库
USE pm;
--创建BL层内部表
CREATE TABLE IF NOT EXISTS pm.tl_pm_recommend_strategy_d
(
day_id string comment '{"chs_name":"当天日期","description":"","etl":"","value":"","remark":""}',
device_os_type string comment '{"chs_name":"设备类型","description":"","etl":"","value":"","remark":""}',
active_type string comment '{"chs_name":"活跃类型","description":"","etl":"","value":"","remark":""}',
card_content_type string comment '{"chs_name":"卡片类型","description":"","etl":"","value":"","remark":""}',
recommend_type string comment '{"chs_name":"推荐类型","description":"","etl":"","value":"","remark":""}',
card_click BIGINT comment '{"chs_name":"首页卡片点击PV","description":"","etl":"","value":"","remark":""}',
card_exposure BIGINT comment '{"chs_name":"首页卡片精准曝光PV","description":"","etl":"","value":"","remark":""}',
total_second_click BIGINT comment '{"chs_name":"来自首页卡片的总商业二跳pv(包含页面上搜索及卡片点击)","description":"","etl":"","value":"","remark":""}',
avg_page_stay double comment '{"chs_name":"来自首页卡片的单PV平均浏览时长","description":"","etl":"","value":"","remark":""}',
navbar_search BIGINT comment '{"chs_name":"来自首页卡片的搜索框+搜索按钮点击PV","description":"","etl":"","value":"","remark":""}',
highlight_word BIGINT comment '{"chs_name":"来自首页卡片的文内搜索点击PV","description":"","etl":"","value":"","remark":""}',
self_welfare_card BIGINT comment '{"chs_name":"来自首页卡片的商品卡片点击PV","description":"","etl":"","value":"","remark":""}',
recommend_welfare_card BIGINT comment '{"chs_name":"来自首页卡片的推荐商品+查看全部商品点击pv","description":"","etl":"","value":"","remark":""}',
recommend_content_card BIGINT comment '{"chs_name":"来自首页卡片的推荐内容点击pv","description":"","etl":"","value":"","remark":""}',
recommend_special_card BIGINT comment '{"chs_name":"来自首页卡片的推荐专题点击pv","description":"","etl":"","value":"","remark":""}',
transfer_card BIGINT comment '{"chs_name":"来自首页卡片的转诊点击pv","description":"","etl":"","value":"","remark":""}',
video_consultation BIGINT comment '{"chs_name":"来自首页卡片的视频面诊点击pv","description":"","etl":"","value":"","remark":""}'
)comment '首页推荐策略日报'
PARTITIONED BY (PARTITION_DAY STRING comment '分区日期')
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
COLLECTION ITEMS TERMINATED BY '\002'
MAP KEYS TERMINATED BY '\003'
LINES TERMINATED BY '\n'
STORED AS TEXTFILE;
\ No newline at end of file
--***************************************************************
--*脚本名称: create_pm_c_op_co_content_dimen_d.sql
--*功能: 内容日报
--*业务名称: pm
--*输入数据:
--*作者: weiyimin@igengmei.com
--*更新时间: 2020-5-25 11:00
--***************************************************************
--设置全局变量&UDF
SET mapreduce.job.queuename=data;
--使用bl数据库
USE pm;
--创建BL层内部表
CREATE TABLE IF NOT EXISTS pm.tl_pm_search_click_path_d
(
day_id string comment '{"chs_name":"当天日期","description":"","etl":"","value":"","remark":""}',
device_os_type string comment '{"chs_name":"设备类型","description":"","etl":"","value":"","remark":""}',
active_type string comment '{"chs_name":"活跃类型","description":"","etl":"","value":"","remark":""}',
search_entrance string comment '{"chs_name":"搜索入口","description":"","etl":"","value":"","remark":""}',
click_search_pv int comment '{"chs_name":"点击搜索或搜索框pv","description":"","etl":"","value":"","remark":""}',
click_search_uv int comment '{"chs_name":"点击搜索或搜索框uv","description":"","etl":"","value":"","remark":""}'
)comment '分搜索入口的搜索点击数据'
PARTITIONED BY (PARTITION_DAY STRING comment '分区日期')
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
COLLECTION ITEMS TERMINATED BY '\002'
MAP KEYS TERMINATED BY '\003'
LINES TERMINATED BY '\n'
STORED AS TEXTFILE;
\ No newline at end of file
--***************************************************************
--*脚本名称: create_pm_c_op_co_content_dimen_d.sql
--*功能: 内容日报
--*业务名称: pm
--*输入数据:
--*作者: weiyimin@igengmei.com
--*更新时间: 2020-5-25 11:00
--***************************************************************
--设置全局变量&UDF
SET mapreduce.job.queuename=data;
--使用bl数据库
USE pm;
--创建BL层内部表
CREATE TABLE IF NOT EXISTS pm.tl_pm_search_input_type_d
(
day_id string comment '{"chs_name":"当天日期","description":"","etl":"","value":"","remark":""}',
query string comment '{"chs_name":"搜索词","description":"","etl":"","value":"","remark":""}',
input_type string comment '{"chs_name":"搜索方式","description":"","etl":"","value":"","remark":""}',
search_pv bigint comment '{"chs_name":"搜索量","description":"","etl":"","value":"","remark":""}'
)comment '分方式搜索日报'
PARTITIONED BY (PARTITION_DAY STRING comment '分区日期')
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
COLLECTION ITEMS TERMINATED BY '\002'
MAP KEYS TERMINATED BY '\003'
LINES TERMINATED BY '\n'
STORED AS TEXTFILE;
\ No newline at end of file
--***************************************************************
--*脚本名称: create_pm_c_op_co_content_dimen_d.sql
--*功能: 内容日报
--*业务名称: pm
--*输入数据:
--*作者: weiyimin@igengmei.com
--*更新时间: 2020-5-25 11:00
--***************************************************************
--设置全局变量&UDF
SET mapreduce.job.queuename=data;
--使用bl数据库
USE pm;
--创建BL层内部表
CREATE TABLE IF NOT EXISTS pm.tl_pm_search_result_click_rate_d
(
day_id string comment '{"chs_name":"当天日期","description":"","etl":"","value":"","remark":""}',
query string comment '{"chs_name":"设备类型","description":"","etl":"","value":"","remark":""}',
search_pv bigint comment '{"chs_name":"活跃类型","description":"","etl":"","value":"","remark":""}',
search_uv bigint comment '{"chs_name":"搜索入口","description":"","etl":"","value":"","remark":""}',
search_more_pv bigint comment '{"chs_name":"综合tab下的搜索的点击pv","description":"","etl":"","value":"","remark":""}',
page_more_pv bigint comment '{"chs_name":"搜索综合结果页浏览pv","description":"","etl":"","value":"","remark":""}',
more_click_pv bigint comment '{"chs_name":"搜索综合结果页内容卡片点击PV","description":"","etl":"","value":"","remark":""}',
more_click_10_pv bigint comment '{"chs_name":"搜索综合结果页前10内容卡片点击PV","description":"","etl":"","value":"","remark":""}',
more_click_5_diary_pv bigint comment '{"chs_name":"搜索综合结果页前5日记卡片点击PV","description":"","etl":"","value":"","remark":""}',
more_click_5_answer_pv bigint comment '{"chs_name":"搜索综合结果页前5回答卡片点击PV","description":"","etl":"","value":"","remark":""}',
more_click_5_topic_pv bigint comment '{"chs_name":"搜索综合结果页前5帖子卡片点击PV","description":"","etl":"","value":"","remark":""}',
search_wel_pv bigint comment '{"chs_name":"美购tab下的搜索的点击pv","description":"","etl":"","value":"","remark":""}',
page_wel_pv bigint comment '{"chs_name":"搜索美购结果页浏览pv","description":"","etl":"","value":"","remark":""}',
wel_click_pv bigint comment '{"chs_name":"搜索美购结果页卡片点击PV","description":"","etl":"","value":"","remark":""}',
wel_click_10_pv bigint comment '{"chs_name":"搜索美购结果页前10卡片点击PV","description":"","etl":"","value":"","remark":""}',
wel_click_5_pv bigint comment '{"chs_name":"搜索美购结果页前5卡片点击PV","description":"","etl":"","value":"","remark":""}',
search_diary_pv bigint comment '{"chs_name":"日记tab下的搜索的点击pv","description":"","etl":"","value":"","remark":""}',
page_diary_pv bigint comment '{"chs_name":"搜索日记结果页浏览pv","description":"","etl":"","value":"","remark":""}',
diary_click_pv bigint comment '{"chs_name":"搜索日记结果页卡片点击PV","description":"","etl":"","value":"","remark":""}',
diary_click_10_pv bigint comment '{"chs_name":"搜索日记结果页前10卡片点击PV","description":"","etl":"","value":"","remark":""}',
diary_click_5_pv bigint comment '{"chs_name":"搜索日记结果页前5卡片点击PV","description":"","etl":"","value":"","remark":""}',
search_more_uv bigint comment '{"chs_name":"综合tab下的搜索的点击uv","description":"","etl":"","value":"","remark":""}',
page_more_uv bigint comment '{"chs_name":"搜索综合结果页浏览uv","description":"","etl":"","value":"","remark":""}',
more_click_uv bigint comment '{"chs_name":"搜索综合结果页内容卡片点击UV","description":"","etl":"","value":"","remark":""}',
more_click_10_uv bigint comment '{"chs_name":"搜索综合结果页前10内容卡片点击UV","description":"","etl":"","value":"","remark":""}',
more_click_5_diary_uv bigint comment '{"chs_name":"搜索综合结果页前5日记卡片点击UV","description":"","etl":"","value":"","remark":""}',
more_click_5_answer_uv bigint comment '{"chs_name":"搜索综合结果页前5回答卡片点击UV","description":"","etl":"","value":"","remark":""}',
more_click_5_topic_uv bigint comment '{"chs_name":"搜索综合结果页前5帖子卡片点击UV","description":"","etl":"","value":"","remark":""}',
search_wel_uv bigint comment '{"chs_name":"美购tab下的搜索的点击uv","description":"","etl":"","value":"","remark":""}',
page_wel_uv bigint comment '{"chs_name":"搜索美购结果页浏览uv","description":"","etl":"","value":"","remark":""}',
wel_click_uv bigint comment '{"chs_name":"搜索美购结果页卡片点击UV","description":"","etl":"","value":"","remark":""}',
wel_click_10_uv bigint comment '{"chs_name":"搜索美购结果页前10卡片点击UV","description":"","etl":"","value":"","remark":""}',
wel_click_5_uv bigint comment '{"chs_name":"搜索美购结果页前5卡片点击UV","description":"","etl":"","value":"","remark":""}',
search_diary_uv bigint comment '{"chs_name":"日记tab下的搜索的点击uv","description":"","etl":"","value":"","remark":""}',
page_diary_uv bigint comment '{"chs_name":"搜索日记结果页浏览uv","description":"","etl":"","value":"","remark":""}',
diary_click_uv bigint comment '{"chs_name":"搜索日记结果页卡片点击UV","description":"","etl":"","value":"","remark":""}',
diary_click_10_uv bigint comment '{"chs_name":"搜索日记结果页前10卡片点击UV","description":"","etl":"","value":"","remark":""}',
diary_click_5_uv bigint comment '{"chs_name":"搜索日记结果页前5卡片点击UV","description":"","etl":"","value":"","remark":""}'
)comment '分搜索词日报'
PARTITIONED BY (PARTITION_DAY STRING comment '分区日期')
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
COLLECTION ITEMS TERMINATED BY '\002'
MAP KEYS TERMINATED BY '\003'
LINES TERMINATED BY '\n'
STORED AS TEXTFILE;
\ No newline at end of file
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