| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773 |
- --@exclude_input=loghubods.video_action_log_flow_new
- --@exclude_input=loghubods.user_share_log_flow
- --*********************
- -- alg_recsys_rank_labelmatch_20250108
- --*********************
- --drop table loghubods.dwd_recsys_alg_exposure_base_20250108;
- CREATE TABLE IF NOT EXISTS loghubods.dwd_recsys_alg_exposure_base_20250108
- (
- apptype STRING
- ,uid STRING
- ,mid STRING
- ,vid STRING
- ,sessionid STRING
- ,subsessionid STRING
- ,pagesource STRING
- ,page STRING
- ,recommendlogvo STRING COMMENT '推荐算法的返回结果日志存在这个字段中'
- ,abcode STRING COMMENT '推荐算法的ab分组:ab0'
- ,recommendpagetype STRING COMMENT '用于区分pagesource相同时某些场景的。三种回流头部;两种下滑-沉浸页下滑和feed下滑。 -pages/user-videos-share-recommend-detail 是沉浸页。'
- ,recomtraceid STRING COMMENT '在后端调取推荐服务之前生成。前端降级会空;后端也可能为空。'
- ,headvideoid STRING
- ,rootsourceid STRING COMMENT '区分touliu等流量,咨询产品。'
- ,hotsencetype STRING
- ,flowpool STRING COMMENT '非流量池,是空字符串。没有null值。'
- ,level STRING COMMENT '非流量池,是null。'
- ,clientip STRING
- ,machineinfo_brand STRING
- ,machineinfo_model STRING
- ,machineinfo_system STRING
- ,machineinfo_wechatversion STRING
- ,machineinfo_sdkversion STRING
- ,province STRING
- ,city STRING
- ,ts STRING
- ,is_share STRING
- ,share_cnt STRING
- ,is_return_1 STRING
- ,return_1_pv STRING
- ,return_1_uv STRING
- ,return_1_mids STRING
- ,is_return_n STRING
- ,return_n_pv STRING
- ,return_n_uv STRING
- ,return_n_mids STRING
- ,is_return_noself STRING
- ,return_1_uv_noself STRING
- ,return_1_mids_noself STRING
- ,is_return_n_noself STRING
- ,return_n_uv_noself STRING
- ,return_n_mids_noself STRING
- ,new_exposure_cnt STRING
- ,extend STRING
- )
- PARTITIONED BY
- (
- dt STRING COMMENT '日期:20240105'
- ,hh STRING COMMENT '小时:04'
- )
- STORED AS ALIORC
- TBLPROPERTIES ('comment' = '推荐算法-labelmatch表-20250108更新最新版')
- LIFECYCLE 3650
- ;
- SET hive.exec.dynamic.partition = true
- ;
- SET hive.exec.dynamic.partition.mode = nonstrict
- ;
- SET odps.stage.mapper.split.size = 1024
- ;
- INSERT OVERWRITE TABLE loghubods.dwd_recsys_alg_exposure_base_20250108 PARTITION (dt,hh)
- WITH t_return AS
- (
- SELECT *
- ,CONCAT(dthh,":",shareid,":",vid,":",dthh_id) AS id
- FROM (
- SELECT CONCAT(year,month,day,hour) AS dthh
- ,apptype
- ,machinecode AS mid
- ,clickobjectid AS vid
- ,sessionid
- ,subsessionid -- 注意这是回流对应的subsessionid,每次回流点击会重置,可以通过这个字段找到回流的曝光。
- ,shareid
- ,rootshareid
- ,CAST(clienttimestamp / 1000 AS BIGINT) AS ts
- ,ROW_NUMBER() OVER (PARTITION BY CONCAT(year,month,day,hour),apptype,machinecode,clickobjectid,sessionid,subsessionid,shareid,rootshareid ORDER BY clienttimestamp DESC ) AS rn
- ,ROW_NUMBER() OVER (PARTITION BY CONCAT(year,month,day,hour),shareid,clickobjectid ORDER BY clienttimestamp ) AS dthh_id
- FROM loghubods.user_share_log_flow -- 回流行为,理应subsessionid只有一条,但有脏数据,去重。
- WHERE CONCAT(year,month,day,hour) BETWEEN TO_CHAR(FROM_UNIXTIME(UNIX_TIMESTAMP(TO_DATE('${dt}${hh}','YYYYMMDDHH')) - 3600 * 25),'YYYYMMDDHH') AND TO_CHAR(FROM_UNIXTIME(UNIX_TIMESTAMP(TO_DATE('${dt}${hh}','YYYYMMDDHH')) - 3600 * 1),'YYYYMMDDHH') --WHERE CONCAT(year,month,day,hour) = TO_CHAR(FROM_UNIXTIME(UNIX_TIMESTAMP(TO_DATE('${dt}${hh}','YYYYMMDDHH')) - 3600 * 25),'YYYYMMDDHH')
- AND __topic__ = 'click'
- AND apptype IS NOT NULL
- AND apptype NOT IN ('12') -- 12的pagesoucre是h5-share和h5-detail 暂时过滤掉 不做处理
- AND machinecode IS NOT NULL
- AND clickobjectid IS NOT NULL
- AND pagesource REGEXP "-pages/user-videos-share$" -- 存在脏数据 vlog-gzh /mine/mine-info$ 结尾的,都过滤掉。
- )
- WHERE rn = 1
- )
- ,t_share_from_sharelog AS
- (
- SELECT *
- FROM (
- SELECT CONCAT(year,month,day,hour) AS dthh
- ,apptype
- ,machinecode AS mid
- ,shareobjectid AS vid
- ,sessionid
- ,subsessionid
- ,pagesource
- ,shareid
- ,CAST(clienttimestamp / 1000 AS BIGINT) AS ts
- ,ROW_NUMBER() OVER (PARTITION BY CONCAT(year,month,day,hour),apptype,machinecode,shareobjectid,sessionid,subsessionid,pagesource,shareid ORDER BY clienttimestamp DESC ) AS rn
- FROM loghubods.user_share_log_flow
- WHERE CONCAT(year,month,day,hour) BETWEEN TO_CHAR(FROM_UNIXTIME(UNIX_TIMESTAMP(TO_DATE('${dt}${hh}','YYYYMMDDHH')) - 3600 * 25),'YYYYMMDDHH') AND TO_CHAR(FROM_UNIXTIME(UNIX_TIMESTAMP(TO_DATE('${dt}${hh}','YYYYMMDDHH')) - 3600 * 1),'YYYYMMDDHH') --WHERE CONCAT(year,month,day,hour) = TO_CHAR(FROM_UNIXTIME(UNIX_TIMESTAMP(TO_DATE('${dt}${hh}','YYYYMMDDHH')) - 3600 * 25),'YYYYMMDDHH')
- AND __topic__ = 'share'
- AND apptype IS NOT NULL
- AND apptype NOT IN ('12')
- AND machinecode IS NOT NULL
- AND shareobjectid IS NOT NULL
- )
- WHERE rn = 1
- )
- ,t_exposure AS
- (
- SELECT dthh_id
- ,dthh
- ,apptype
- ,uid
- ,mid
- ,vid
- ,sessionid
- ,subsessionid
- ,rootsessionid_new
- ,pagesource
- ,recommendlogvo
- ,abcode
- ,recommendpagetype
- ,recomtraceid
- ,headvideoid
- ,rootsourceid
- ,hotsencetype
- ,animationscenetype
- ,JSON_PARSE(IF(JSON_VALID(extparams),extparams,"{}")) AS extParams
- ,flowpool
- ,level
- ,clientip
- ,machineinfo_brand
- ,machineinfo_model
- ,machineinfo_system
- ,machineinfo_wechatversion
- ,machineinfo_sdkversion
- ,province
- ,city
- ,versioncode
- ,ts
- ,rn
- ,id
- ,dt
- ,hh
- FROM loghubods.dwd_recsys_alg_exposure_base_view_20250402
- WHERE CONCAT(dt,hh) BETWEEN TO_CHAR(FROM_UNIXTIME(UNIX_TIMESTAMP(TO_DATE('${dt}${hh}','YYYYMMDDHH')) - 3600 * 25),'YYYYMMDDHH') AND TO_CHAR(FROM_UNIXTIME(UNIX_TIMESTAMP(TO_DATE('${dt}${hh}','YYYYMMDDHH')) - 3600 * 1),'YYYYMMDDHH')
- )
- ,t_exposure_recommend AS
- (
- SELECT *
- FROM t_exposure
- WHERE pagesource REGEXP 'category$|recommend$|-pages/user-videos-detail$'
- )
- ,t_return_exposure_1 AS -- 曝光关联回流,用于计算viewh24
- (
- SELECT *
- FROM (
- SELECT t1.id AS exposure_id
- ,t1.mid AS mid
- ,t1.vid AS vid
- ,t1.subsessionid AS subsessionid
- ,t1.sessionid AS sessionid
- ,t1.headvideoid AS headvideoid
- ,t1.dthh
- ,t2.id AS return_id
- ,ROW_NUMBER() OVER (PARTITION BY t1.id ORDER BY t2.ts DESC ) AS rn
- FROM t_exposure_recommend t1
- LEFT JOIN t_return t2
- ON t1.mid = t2.mid
- AND t1.headvideoid = t2.vid
- AND t1.subsessionid = t2.subsessionid
- )
- WHERE rn = 1
- )
- ,t_return_exposure_2 AS -- 曝光关联回流,用于计算viewh24
- (
- SELECT *
- FROM (
- SELECT t1.exposure_id AS exposure_id
- ,t1.mid AS mid
- ,t1.vid AS vid
- ,t1.subsessionid AS subsessionid
- ,t1.sessionid AS sessionid
- ,t1.headvideoid AS headvideoid
- ,t1.dthh
- ,t2.id AS return_id
- ,ROW_NUMBER() OVER (PARTITION BY t1.exposure_id ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_return_exposure_1
- WHERE return_id IS NULL
- ) t1
- LEFT JOIN t_return t2
- ON t1.mid = t2.mid
- AND t1.headvideoid = t2.vid
- AND t1.sessionid = t2.sessionid
- )
- WHERE rn = 1
- )
- ,t_return_exposure_3 AS -- 曝光关联回流,用于计算viewh24
- (
- SELECT *
- FROM (
- SELECT t1.exposure_id AS exposure_id
- ,t1.mid AS mid
- ,t1.vid AS vid
- ,t1.subsessionid AS subsessionid
- ,t1.sessionid AS sessionid
- ,t1.headvideoid AS headvideoid
- ,t1.dthh
- ,t2.id AS return_id
- ,ROW_NUMBER() OVER (PARTITION BY t1.exposure_id ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_return_exposure_2
- WHERE return_id IS NULL
- ) t1
- LEFT JOIN t_return t2
- ON t1.mid = t2.mid
- AND t1.subsessionid = t2.subsessionid
- )
- WHERE rn = 1
- )
- ,t_return_exposure_4 AS -- 曝光关联回流,用于计算viewh24
- (
- SELECT *
- FROM (
- SELECT t1.exposure_id AS exposure_id
- ,t1.mid AS mid
- ,t1.vid AS vid
- ,t1.subsessionid AS subsessionid
- ,t1.sessionid AS sessionid
- ,t1.headvideoid AS headvideoid
- ,t1.dthh
- ,t2.id AS return_id
- ,ROW_NUMBER() OVER (PARTITION BY t1.exposure_id ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_return_exposure_3
- WHERE return_id IS NULL
- ) t1
- LEFT JOIN t_return t2
- ON t1.mid = t2.mid
- AND t1.sessionid = t2.sessionid
- )
- WHERE rn = 1
- )
- ,t_return_exposure AS
- (
- SELECT a.*
- ,b.exposure_cnt AS new_exposure_cnt
- FROM t_return a
- LEFT JOIN (
- SELECT return_id
- ,COUNT(1) AS exposure_cnt
- FROM (
- SELECT *
- FROM t_return_exposure_1
- WHERE return_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_return_exposure_2
- WHERE return_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_return_exposure_3
- WHERE return_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_return_exposure_4
- WHERE return_id IS NOT NULL
- )
- GROUP BY return_id
- ) b
- ON a.id = b.return_id
- )
- ,t_normal_share_exposure_1 AS -- 开始处理常规的分享与曝光关联
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM t_share_from_sharelog t1
- LEFT JOIN t_exposure t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.subsessionid = t2.subsessionid
- AND t1.pagesource = t2.pagesource
- AND t1.ts >= t2.ts
- WHERE t1.pagesource NOT REGEXP "pages/detail-user-videos-share-recommend$"
- )
- WHERE rn = 1
- )
- ,t_normal_share_exposure_2 AS
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_normal_share_exposure_1
- WHERE exposure_id IS NULL
- ) t1
- LEFT JOIN t_exposure t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.sessionid = t2.sessionid
- AND t1.pagesource = t2.pagesource
- AND t1.ts >= t2.ts
- )
- WHERE rn = 1
- )
- ,t_normal_share_exposure_3 AS
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_normal_share_exposure_2
- WHERE exposure_id IS NULL
- ) t1
- LEFT JOIN t_exposure t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.subsessionid = t2.subsessionid
- AND t1.pagesource = t2.pagesource
- )
- WHERE rn = 1
- )
- ,t_normal_share_exposure_4 AS
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_normal_share_exposure_3
- WHERE exposure_id IS NULL
- ) t1
- LEFT JOIN t_exposure t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.sessionid = t2.sessionid
- AND t1.pagesource = t2.pagesource
- )
- WHERE rn = 1
- )
- ,t_normal_share_exposure_5 AS
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_normal_share_exposure_4
- WHERE exposure_id IS NULL
- ) t1
- LEFT JOIN t_exposure t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.subsessionid = t2.subsessionid
- )
- WHERE rn = 1
- )
- ,t_normal_share_exposure_6 AS
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_normal_share_exposure_5
- WHERE exposure_id IS NULL
- ) t1
- LEFT JOIN t_exposure t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.sessionid = t2.sessionid
- )
- WHERE rn = 1
- )
- ,t_exposure_detail AS
- (
- SELECT *
- FROM t_exposure
- WHERE pagesource REGEXP "-pages/user-videos-detail$|pages/detail-recommend$"
- )
- ,t_no_normal_share_exposure_1 AS -- 开始处理非常规的分享与曝光关联
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM t_share_from_sharelog t1
- LEFT JOIN t_exposure_detail t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.subsessionid = t2.subsessionid
- AND t1.ts >= t2.ts
- WHERE t1.pagesource REGEXP "pages/detail-user-videos-share-recommend$"
- )
- WHERE rn = 1
- )
- ,t_no_normal_share_exposure_2 AS
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_no_normal_share_exposure_1
- WHERE exposure_id IS NULL
- ) t1
- LEFT JOIN t_exposure_detail t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.sessionid = t2.sessionid
- AND t1.ts >= t2.ts
- )
- WHERE rn = 1
- )
- ,t_no_normal_share_exposure_3 AS
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_no_normal_share_exposure_2
- WHERE exposure_id IS NULL
- ) t1
- LEFT JOIN t_exposure_detail t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.subsessionid = t2.subsessionid
- )
- WHERE rn = 1
- )
- ,t_no_normal_share_exposure_4 AS
- (
- SELECT *
- FROM (
- SELECT t1.dthh
- ,t1.apptype
- ,t1.mid
- ,t1.vid
- ,t1.sessionid
- ,t1.subsessionid
- ,t1.pagesource
- ,t1.shareid
- ,t1.ts
- ,t2.id AS exposure_id
- ,t2.ts AS exposure_ts
- ,ROW_NUMBER() OVER (PARTITION BY t1.dthh,t1.apptype,t1.mid,t1.vid,t1.sessionid,t1.subsessionid,t1.pagesource,t1.shareid ORDER BY t2.ts DESC ) AS rn
- FROM (
- SELECT *
- FROM t_no_normal_share_exposure_3
- WHERE exposure_id IS NULL
- ) t1
- LEFT JOIN t_exposure_detail t2
- ON t1.apptype = t2.apptype
- AND t1.mid = t2.mid
- AND t1.vid = t2.vid
- AND t1.sessionid = t2.sessionid
- )
- WHERE rn = 1
- )
- ,t_share_exposure AS
- (
- SELECT *
- FROM t_normal_share_exposure_1
- WHERE exposure_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_normal_share_exposure_2
- WHERE exposure_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_normal_share_exposure_3
- WHERE exposure_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_normal_share_exposure_4
- WHERE exposure_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_normal_share_exposure_5
- WHERE exposure_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_normal_share_exposure_6
- UNION ALL
- SELECT *
- FROM t_no_normal_share_exposure_1
- WHERE exposure_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_no_normal_share_exposure_2
- WHERE exposure_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_no_normal_share_exposure_3
- WHERE exposure_id IS NOT NULL
- UNION ALL
- SELECT *
- FROM t_no_normal_share_exposure_4
- )
- ,t_share_with_label AS
- (
- SELECT a.dthh
- ,a.apptype -- join 条件
- ,a.mid
- ,a.vid -- join 条件
- ,a.sessionid
- ,a.subsessionid
- ,a.pagesource
- ,a.shareid -- join 条件
- ,a.ts
- ,a.exposure_id
- ,COALESCE(b.return_1_pv,0) AS return_1_pv
- ,COALESCE(b.return_1_uv,0) AS return_1_uv
- ,b.return_1_mids AS return_1_mids -- 可能为null,再决策是否提前处理。
- ,COALESCE(c.return_n_pv,0) AS return_n_pv
- ,COALESCE(c.return_n_uv,0) AS return_n_uv
- ,c.return_n_mids AS return_n_mids -- 可能为null,再决策是否提前处理。
- ,COALESCE(c.new_exposure_cnt,0) AS new_exposure_cnt
- FROM t_share_exposure a
- LEFT JOIN (
- SELECT shareid
- ,vid
- ,apptype
- ,COUNT(1) AS return_1_pv
- ,COUNT(DISTINCT mid) AS return_1_uv
- ,CONCAT_WS(',',COLLECT_SET(mid)) AS return_1_mids
- FROM t_return
- GROUP BY shareid
- ,vid
- ,apptype
- ) b
- ON a.shareid = b.shareid
- AND a.vid = b.vid
- AND a.apptype = b.apptype
- LEFT JOIN (
- SELECT rootshareid
- ,vid
- ,apptype
- ,COUNT(1) AS return_n_pv
- ,COUNT(DISTINCT mid) AS return_n_uv
- ,CONCAT_WS(',',COLLECT_SET(mid)) AS return_n_mids
- ,SUM(new_exposure_cnt) AS new_exposure_cnt
- FROM t_return_exposure
- GROUP BY rootshareid
- ,vid
- ,apptype
- ) c
- ON a.shareid = c.rootshareid
- AND a.vid = c.vid
- AND a.apptype = c.apptype
- )
- ,t_share_with_label_group AS
- (
- SELECT exposure_id
- ,COUNT(1) AS share_cnt
- ,SUM(return_1_pv) AS return_1_pv
- ,COALESCE(SIZE(SPLIT(DEDUPLICATION4LIST(CONCAT_WS(',',COLLECT_LIST(return_1_mids))),",")),0) AS return_1_uv
- ,DEDUPLICATION4LIST(CONCAT_WS(',',COLLECT_LIST(return_1_mids))) AS return_1_mids -- 可能是null
- ,SUM(return_n_pv) AS return_n_pv
- ,COALESCE(SIZE(SPLIT(DEDUPLICATION4LIST(CONCAT_WS(',',COLLECT_LIST(return_n_mids))),",")),0) AS return_n_uv
- ,DEDUPLICATION4LIST(CONCAT_WS(',',COLLECT_LIST(return_n_mids))) AS return_n_mids -- 可能是null
- ,SUM(new_exposure_cnt) AS new_exposure_cnt
- FROM t_share_with_label
- GROUP BY exposure_id
- )
- ,t_root_source_id_group_name AS
- (
- SELECT *
- FROM (
- SELECT root_source_id
- ,group_name
- ,ROW_NUMBER() OVER (PARTITION BY root_source_id ) AS rn
- FROM loghubods.changwen_rootsourceid_group_hour
- WHERE dt = MAX_PT('loghubods.changwen_rootsourceid_group_hour')
- )
- WHERE rn = 1
- )
- ,t_exposure_share_return AS
- (
- SELECT apptype
- ,uid
- ,mid
- ,vid
- ,sessionid
- ,subsessionid
- ,pagesource
- ,CASE WHEN pagesource REGEXP 'pages/user-videos-share-recommend$' THEN '回流后沉浸页&内页feed'
- WHEN pagesource REGEXP 'pages/detail-recommend$' THEN '详情后沉浸页'
- WHEN pagesource REGEXP 'pages/user-videos-share$' THEN '回流页'
- WHEN pagesource REGEXP 'pages/user-videos-detail$' THEN '详情页'
- WHEN pagesource REGEXP 'pages/category$' THEN '首页feed'
- ELSE '其他'
- END AS pagesource_new
- ,recommendlogvo -- 推荐算法的返回结果日志存在这个字段中
- ,abcode -- 推荐算法的ab分组
- ,recommendpagetype -- 三种回流头部;两种下滑-沉浸页下滑和feed下滑
- ,recomtraceid
- ,headvideoid
- ,rootsourceid
- ,hotsencetype
- ,flowpool -- 14#68#3#1735262438476#2
- ,level
- ,clientip
- ,machineinfo_brand
- ,machineinfo_model
- ,machineinfo_system
- ,machineinfo_wechatversion
- ,machineinfo_sdkversion
- ,province
- ,city
- ,ts
- ,IF(COALESCE(share_cnt,0) > 0,1,0) AS is_share
- ,COALESCE(share_cnt,0) AS share_cnt
- ,IF(COALESCE(return_1_uv,0) > 0,1,0) AS is_return_1
- ,COALESCE(return_1_pv,0) AS return_1_pv
- ,COALESCE(return_1_uv,0) AS return_1_uv
- ,return_1_mids -- 可能是null
- ,IF(COALESCE(return_n_pv,0) > 0,1,0) AS is_return_n
- ,COALESCE(return_n_pv,0) AS return_n_pv
- ,COALESCE(return_n_uv,0) AS return_n_uv
- ,return_n_mids -- 可能是null
- ,IF(COALESCE(COALESCE(SIZE(ARRAY_REMOVE(SPLIT(return_1_mids,","),mid)),0),0) > 0,1,0) AS is_return_noself
- ,COALESCE(SIZE(ARRAY_REMOVE(SPLIT(return_1_mids,","),mid)),0) AS return_1_uv_noself
- ,ARRAY_JOIN(ARRAY_REMOVE(SPLIT(return_1_mids,","),mid),",") AS return_1_mids_noself
- ,IF(COALESCE(COALESCE(SIZE(ARRAY_REMOVE(SPLIT(return_n_mids,","),mid)),0),0) > 0,1,0) AS is_return_n_noself
- ,COALESCE(SIZE(ARRAY_REMOVE(SPLIT(return_n_mids,","),mid)),0) AS return_n_uv_noself
- ,ARRAY_JOIN(ARRAY_REMOVE(SPLIT(return_n_mids,","),mid),",") AS return_n_mids_noself
- ,COALESCE(new_exposure_cnt) AS new_exposure_cnt
- ,JSON_FORMAT(
- JSON_OBJECT("animationSceneType",animationSceneType,"extParams",extParams,"rootsessionid",rootsessionid_new,"versioncode",versioncode,"group_name",tc.group_name)
- ) AS extend
- ,SUBSTR(dthh,1,8) AS dt
- ,SUBSTR(dthh,9,2) AS hh
- FROM t_exposure ta
- LEFT JOIN t_share_with_label_group tb
- ON ta.id = tb.exposure_id
- LEFT JOIN t_root_source_id_group_name tc
- ON ta.rootsourceid = tc.root_source_id
- )SELECT *
- FROM t_exposure_share_return
- ;
|