|
|
@@ -0,0 +1,371 @@
|
|
|
+-- base_v4_v1_分层: apptype=0, 在 base_v4_v1 基础上新增 source_type(内部/外部) × layer_type(首层/裂变层) 两个维度
|
|
|
+-- 总体行通过 GROUPING SETS 同时输出
|
|
|
+WITH t_abmap AS
|
|
|
+(
|
|
|
+ SELECT "a" AS suffix, "前基线" AS abcode
|
|
|
+ UNION ALL SELECT "b", "前基线"
|
|
|
+ UNION ALL SELECT "e", "实验组：解构特征排序str模型&召回"
|
|
|
+ UNION ALL SELECT "f", "实验组：解构特征排序str模型&召回"
|
|
|
+ UNION ALL SELECT "5", "实验组：解构特征排序str模型"
|
|
|
+ UNION ALL SELECT "d", "实验组：解构特征排序str模型"
|
|
|
+ UNION ALL SELECT "3", "实验组：bn_ros新损失函数"
|
|
|
+ UNION ALL SELECT "4", "实验组：bn_ros新损失函数"
|
|
|
+ UNION ALL SELECT "6", "实验组：cn_rov"
|
|
|
+ UNION ALL SELECT "7", "实验组：cn_rov"
|
|
|
+ UNION ALL SELECT "0", "实验组：建模目标实验"
|
|
|
+ UNION ALL SELECT "1", "实验组：建模目标实验"
|
|
|
+ UNION ALL SELECT "8", "对照组"
|
|
|
+ UNION ALL SELECT "9", "对照组"
|
|
|
+)
|
|
|
+,t_base AS
|
|
|
+(
|
|
|
+ SELECT sub.*
|
|
|
+ ,COALESCE(m.abcode,"other") AS abcode
|
|
|
+ FROM (
|
|
|
+ SELECT dt
|
|
|
+ ,apptype
|
|
|
+ ,SUBSTR(GET_JSON_OBJECT(extend,'$.rootsessionid'),LENGTH(GET_JSON_OBJECT(extend,'$.rootsessionid')),1) AS suffix
|
|
|
+ ,CASE WHEN page IN ("回流后沉浸页&内页feed","详情后沉浸页","首页feed","详情页") THEN "推荐"
|
|
|
+ WHEN page IN ("回流页","其他") THEN "非推荐"
|
|
|
+ ELSE "其他"
|
|
|
+ END AS page
|
|
|
+ ,CASE WHEN a.rootsourceid = '' OR a.rootsourceid IS NULL THEN '内部' ELSE '外部' END AS source_type
|
|
|
+ ,CASE WHEN GET_JSON_OBJECT(a.extend,'$.rootsessionid') = a.subsessionid THEN '首层' ELSE '裂变层' END AS layer_type
|
|
|
+ ,a.mid
|
|
|
+ ,a.vid
|
|
|
+ ,is_share
|
|
|
+ ,share_cnt
|
|
|
+ ,is_return_1
|
|
|
+ ,is_return_n
|
|
|
+ ,is_return_noself
|
|
|
+ ,return_1_uv
|
|
|
+ ,return_n_uv
|
|
|
+ ,return_n_uv_noself
|
|
|
+ ,new_exposure_cnt
|
|
|
+ ,flowpool
|
|
|
+ ,cc.cn
|
|
|
+ ,cc.c1
|
|
|
+ ,dd.dn
|
|
|
+ ,dd.d1
|
|
|
+ FROM loghubods.dwd_recsys_alg_exposure_base_20250108 a
|
|
|
+ LEFT JOIN (
|
|
|
+ SELECT a.machinecode AS mid
|
|
|
+ ,a.subsessionid
|
|
|
+ ,a.videoid AS vid
|
|
|
+ ,COUNT(DISTINCT CASE WHEN b1.machinecode <> b2.machinecode THEN b2.machinecode END) AS cn
|
|
|
+ ,COUNT(DISTINCT CASE WHEN b2.sharedepth = 1 AND b1.machinecode <> b2.machinecode THEN b2.machinecode END) AS c1
|
|
|
+ FROM (
|
|
|
+ SELECT DISTINCT machinecode
|
|
|
+ ,shareobjectid AS videoid
|
|
|
+ ,recomTraceId
|
|
|
+ ,subsessionid
|
|
|
+ ,sharedepth
|
|
|
+ ,shareid
|
|
|
+ FROM loghubods.user_share_log
|
|
|
+ WHERE dt = '${dt}'
|
|
|
+ AND topic = 'share'
|
|
|
+ AND pagesource REGEXP 'category$|recommend$|-pages/user-videos-detail$'
|
|
|
+ ) a
|
|
|
+ LEFT JOIN (
|
|
|
+ SELECT DISTINCT machinecode
|
|
|
+ ,clickobjectid
|
|
|
+ ,recomTraceId
|
|
|
+ ,subsessionid
|
|
|
+ ,sharedepth
|
|
|
+ ,rootshareid
|
|
|
+ FROM loghubods.user_share_log
|
|
|
+ WHERE dt = '${dt}'
|
|
|
+ AND topic = 'click'
|
|
|
+ ) b
|
|
|
+ ON a.shareid = b.rootshareid
|
|
|
+ LEFT JOIN (
|
|
|
+ SELECT DISTINCT machinecode
|
|
|
+ ,shareobjectid
|
|
|
+ ,recomTraceId
|
|
|
+ ,subsessionid
|
|
|
+ ,sharedepth
|
|
|
+ ,shareid
|
|
|
+ FROM loghubods.user_share_log
|
|
|
+ WHERE dt = '${dt}'
|
|
|
+ AND topic = 'share'
|
|
|
+ AND pagesource REGEXP 'category$|recommend$|-pages/user-videos-detail$'
|
|
|
+ ) b1
|
|
|
+ ON b.machinecode = b1.machinecode
|
|
|
+ AND b.subsessionid = b1.subsessionid
|
|
|
+ LEFT JOIN (
|
|
|
+ SELECT DISTINCT machinecode
|
|
|
+ ,clickobjectid
|
|
|
+ ,recomTraceId
|
|
|
+ ,subsessionid
|
|
|
+ ,sharedepth
|
|
|
+ ,shareid
|
|
|
+ ,rootshareid
|
|
|
+ FROM loghubods.user_share_log
|
|
|
+ WHERE dt = '${dt}'
|
|
|
+ AND topic = 'click'
|
|
|
+ ) b2
|
|
|
+ ON b1.shareid = b2.rootshareid
|
|
|
+ GROUP BY a.machinecode
|
|
|
+ ,a.subsessionid
|
|
|
+ ,a.videoid
|
|
|
+ ) cc
|
|
|
+ ON a.mid = cc.mid
|
|
|
+ AND a.subsessionid = cc.subsessionid
|
|
|
+ AND a.vid = cc.vid
|
|
|
+ LEFT JOIN (
|
|
|
+ SELECT *
|
|
|
+ ,LAG(回流,1,0) OVER (PARTITION BY mid,subsessionid ORDER BY rn DESC) AS dn
|
|
|
+ ,LAG(回流1,1,0) OVER (PARTITION BY mid,subsessionid ORDER BY rn DESC) AS d1
|
|
|
+ FROM (
|
|
|
+ SELECT a.mid AS mid
|
|
|
+ ,a.subsessionid
|
|
|
+ ,a.videoid AS vid
|
|
|
+ ,COUNT(DISTINCT b.shareid) AS 分享次数
|
|
|
+ ,COUNT(DISTINCT CASE WHEN c.machinecode <> b.machinecode THEN c.machinecode END) AS 回流
|
|
|
+ ,COUNT(DISTINCT CASE WHEN c.machinecode <> b.machinecode AND c.sharedepth = 1 THEN c.machinecode END) AS 回流1
|
|
|
+ ,ROW_NUMBER() OVER (PARTITION BY a.subsessionid ORDER BY a.logtimestamp ASC) AS rn
|
|
|
+ FROM (
|
|
|
+ SELECT *
|
|
|
+ FROM (
|
|
|
+ SELECT DISTINCT mid
|
|
|
+ ,subsessionid
|
|
|
+ ,videoid
|
|
|
+ ,logtimestamp
|
|
|
+ ,ROW_NUMBER() OVER (PARTITION BY mid,subsessionid,videoid ORDER BY logtimestamp ASC) AS rn
|
|
|
+ FROM loghubods.video_action_log_rp
|
|
|
+ WHERE dt = '${dt}'
|
|
|
+ AND businesstype = 'videoView'
|
|
|
+ AND pagesource REGEXP 'category$|recommend$|-pages/user-videos-detail$'
|
|
|
+ )
|
|
|
+ WHERE rn = 1
|
|
|
+ ) a
|
|
|
+ LEFT JOIN (
|
|
|
+ SELECT DISTINCT machinecode
|
|
|
+ ,shareobjectid AS videoid
|
|
|
+ ,recomTraceId
|
|
|
+ ,subsessionid
|
|
|
+ ,sharedepth
|
|
|
+ ,shareid
|
|
|
+ ,clienttimestamp
|
|
|
+ FROM loghubods.user_share_log
|
|
|
+ WHERE dt = '${dt}'
|
|
|
+ AND topic = 'share'
|
|
|
+ AND pagesource REGEXP 'category$|recommend$|-pages/user-videos-detail$'
|
|
|
+ ) b
|
|
|
+ ON a.mid = b.machinecode
|
|
|
+ AND a.subsessionid = b.subsessionid
|
|
|
+ AND a.videoid = b.videoid
|
|
|
+ LEFT JOIN (
|
|
|
+ SELECT DISTINCT machinecode
|
|
|
+ ,clickobjectid
|
|
|
+ ,recomTraceId
|
|
|
+ ,subsessionid
|
|
|
+ ,sharedepth
|
|
|
+ ,rootshareid
|
|
|
+ FROM loghubods.user_share_log
|
|
|
+ WHERE dt = '${dt}'
|
|
|
+ AND topic = 'click'
|
|
|
+ ) c
|
|
|
+ ON b.shareid = c.rootshareid
|
|
|
+ GROUP BY a.mid
|
|
|
+ ,a.subsessionid
|
|
|
+ ,a.videoid
|
|
|
+ ,a.logtimestamp
|
|
|
+ )
|
|
|
+ ) dd
|
|
|
+ ON a.mid = dd.mid
|
|
|
+ AND a.subsessionid = dd.subsessionid
|
|
|
+ AND a.vid = dd.vid
|
|
|
+ WHERE dt="${dt}"
|
|
|
+ AND apptype IN ("0")
|
|
|
+ AND page IN ("回流后沉浸页&内页feed","详情后沉浸页","首页feed","详情页","回流页","其他")
|
|
|
+ AND abcode IN ("ab0","ab1","ab2","ab3","ab4","ab8","ab9")
|
|
|
+ AND abcode NOT IN ("ab100")
|
|
|
+ ) sub
|
|
|
+ LEFT JOIN t_abmap m
|
|
|
+ ON sub.apptype = "0"
|
|
|
+ AND sub.suffix = m.suffix
|
|
|
+)
|
|
|
+-- dau2：按单尾号聚合，GROUPING SETS 同时产出分层+总体
|
|
|
+,t_dau2_bucket AS
|
|
|
+(
|
|
|
+ SELECT SUBSTR(sub.dt,1,8) AS dt
|
|
|
+ ,sub.apptype
|
|
|
+ ,COALESCE(m.abcode,"other") AS abcode
|
|
|
+ ,sub.suffix
|
|
|
+ ,COALESCE(sub.source_type,'总体') AS source_type
|
|
|
+ ,COALESCE(sub.layer_type,'总体') AS layer_type
|
|
|
+ ,COUNT(DISTINCT sub.machinecode) AS dau2
|
|
|
+ FROM (
|
|
|
+ SELECT dt
|
|
|
+ ,apptype
|
|
|
+ ,machinecode
|
|
|
+ ,SUBSTR(GET_JSON_OBJECT(extparams,'$.rootSessionId'),LENGTH(GET_JSON_OBJECT(extparams,'$.rootSessionId')),1) AS suffix
|
|
|
+ ,CASE WHEN GET_JSON_OBJECT(extparams,'$.rootSourceId') != '' AND GET_JSON_OBJECT(extparams,'$.rootSourceId') IS NOT NULL THEN '外部' ELSE '内部' END AS source_type
|
|
|
+ ,CASE WHEN GET_JSON_OBJECT(extparams,'$.rootSessionId') = subsessionid
|
|
|
+ OR GET_JSON_OBJECT(extparams,'$.rootSessionId') = sessionid THEN '首层' ELSE '裂变层' END AS layer_type
|
|
|
+ FROM loghubods.useractive_log
|
|
|
+ WHERE dt="${dt}"
|
|
|
+ AND apptype IN ("0")
|
|
|
+ AND GET_JSON_OBJECT(extparams,'$.eventInfos.ab_test003') IN ("ab0","ab1","ab2","ab3","ab4","ab5", "ab6", "ab7", "ab8","ab9")
|
|
|
+ AND GET_JSON_OBJECT(extparams,'$.eventInfos.ab_test003') NOT IN ("ab100")
|
|
|
+ ) sub
|
|
|
+ LEFT JOIN t_abmap m
|
|
|
+ ON sub.apptype = "0"
|
|
|
+ AND sub.suffix = m.suffix
|
|
|
+ GROUP BY SUBSTR(sub.dt,1,8)
|
|
|
+ ,sub.apptype
|
|
|
+ ,COALESCE(m.abcode,"other")
|
|
|
+ ,sub.suffix
|
|
|
+ ,sub.source_type
|
|
|
+ ,sub.layer_type
|
|
|
+ GROUPING SETS (
|
|
|
+ (SUBSTR(sub.dt,1,8), sub.apptype, COALESCE(m.abcode,"other"), sub.suffix, sub.source_type, sub.layer_type),
|
|
|
+ (SUBSTR(sub.dt,1,8), sub.apptype, COALESCE(m.abcode,"other"), sub.suffix)
|
|
|
+ )
|
|
|
+)
|
|
|
+-- dau2：按实验组求尾号均值
|
|
|
+,t_dau2 AS
|
|
|
+(
|
|
|
+ SELECT dt
|
|
|
+ ,apptype
|
|
|
+ ,abcode
|
|
|
+ ,source_type
|
|
|
+ ,layer_type
|
|
|
+ ,AVG(dau2) AS dau2
|
|
|
+ FROM t_dau2_bucket
|
|
|
+ GROUP BY dt
|
|
|
+ ,apptype
|
|
|
+ ,abcode
|
|
|
+ ,source_type
|
|
|
+ ,layer_type
|
|
|
+)
|
|
|
+-- 按单尾号聚合（尾号内 UV 去重），GROUPING SETS 同时产出分层+总体
|
|
|
+,t_bucket AS
|
|
|
+(
|
|
|
+ SELECT dt
|
|
|
+ ,apptype
|
|
|
+ ,abcode
|
|
|
+ ,suffix
|
|
|
+ ,COALESCE(source_type,'总体') AS source_type
|
|
|
+ ,COALESCE(layer_type,'总体') AS layer_type
|
|
|
+ ,COALESCE(COUNT(1) / COUNT(DISTINCT mid),0) AS exp_per_dau
|
|
|
+ ,COALESCE(SUM(is_share) / COUNT(1),0) AS str_one
|
|
|
+ ,COALESCE(SUM(return_n_uv) / SUM(is_share),0) AS ros_one
|
|
|
+ ,COALESCE(SUM(share_cnt) / COUNT(1),0) AS str
|
|
|
+ ,COALESCE(SUM(return_n_uv) / SUM(share_cnt),0) AS ros
|
|
|
+ ,COALESCE(SUM(is_return_1) / COUNT(1),0) AS str_plus
|
|
|
+ ,COALESCE(SUM(return_n_uv) / SUM(is_return_1),0) AS ros_minus
|
|
|
+ ,COALESCE(SUM(return_n_uv) / COUNT(1),0) AS bn_rov
|
|
|
+ ,COALESCE(SUM(c1) / COUNT(1),0) AS c1_rov
|
|
|
+ ,COALESCE(SUM(cn) / COUNT(1),0) AS cn_rov
|
|
|
+ ,COALESCE(SUM(d1) / COUNT(1),0) AS d1_rov
|
|
|
+ ,COALESCE(SUM(dn) / COUNT(1),0) AS dn_rov
|
|
|
+ ,COALESCE(SUM(new_exposure_cnt) / COUNT(1),0) AS vovh24
|
|
|
+ ,COUNT(DISTINCT mid) AS dau
|
|
|
+ ,COUNT(1) AS exp
|
|
|
+ ,COALESCE(SUM(is_share),0) AS is_share
|
|
|
+ ,COALESCE(SUM(share_cnt),0) AS share_cnt
|
|
|
+ ,COALESCE(SUM(is_return_1),0) AS is_return_1
|
|
|
+ ,COALESCE(SUM(return_n_uv),0) AS return_n_uv
|
|
|
+ ,COALESCE(SUM(new_exposure_cnt),0) AS viewh24
|
|
|
+ ,COALESCE(SUM(return_n_uv_noself),0) AS return_n_uv_noself
|
|
|
+ ,COALESCE(SUM(cn),0) AS cn
|
|
|
+ ,COALESCE(SUM(c1),0) AS c1
|
|
|
+ ,COALESCE(SUM(dn),0) AS dn
|
|
|
+ ,COALESCE(SUM(d1),0) AS d1
|
|
|
+ FROM t_base
|
|
|
+ WHERE page = "推荐"
|
|
|
+ GROUP BY dt
|
|
|
+ ,apptype
|
|
|
+ ,abcode
|
|
|
+ ,suffix
|
|
|
+ ,source_type
|
|
|
+ ,layer_type
|
|
|
+ GROUPING SETS (
|
|
|
+ (dt, apptype, abcode, suffix, source_type, layer_type),
|
|
|
+ (dt, apptype, abcode, suffix)
|
|
|
+ )
|
|
|
+)
|
|
|
+-- 按实验组求尾号均值
|
|
|
+,t_metrics AS
|
|
|
+(
|
|
|
+ SELECT dt
|
|
|
+ ,apptype
|
|
|
+ ,abcode
|
|
|
+ ,source_type
|
|
|
+ ,layer_type
|
|
|
+ ,ROUND(AVG(exp_per_dau),2) AS exp_per_dau
|
|
|
+ ,ROUND(AVG(str_one),6) AS str_one
|
|
|
+ ,ROUND(AVG(ros_one),6) AS ros_one
|
|
|
+ ,ROUND(AVG(str),6) AS str
|
|
|
+ ,ROUND(AVG(ros),6) AS ros
|
|
|
+ ,ROUND(AVG(str_plus),6) AS str_plus
|
|
|
+ ,ROUND(AVG(ros_minus),6) AS ros_minus
|
|
|
+ ,ROUND(AVG(bn_rov),6) AS bn_rov
|
|
|
+ ,ROUND(AVG(c1_rov),6) AS c1_rov
|
|
|
+ ,ROUND(AVG(cn_rov),6) AS cn_rov
|
|
|
+ ,ROUND(AVG(d1_rov),6) AS d1_rov
|
|
|
+ ,ROUND(AVG(dn_rov),6) AS dn_rov
|
|
|
+ ,ROUND(AVG(vovh24),6) AS vovh24
|
|
|
+ ,AVG(dau) AS dau
|
|
|
+ ,AVG(exp) AS exp
|
|
|
+ ,AVG(is_share) AS is_share
|
|
|
+ ,AVG(share_cnt) AS share_cnt
|
|
|
+ ,AVG(is_return_1) AS is_return_1
|
|
|
+ ,AVG(return_n_uv) AS return_n_uv
|
|
|
+ ,AVG(viewh24) AS viewh24
|
|
|
+ ,AVG(return_n_uv_noself) AS return_n_uv_noself
|
|
|
+ ,AVG(cn) AS cn
|
|
|
+ ,AVG(c1) AS c1
|
|
|
+ ,AVG(dn) AS dn
|
|
|
+ ,AVG(d1) AS d1
|
|
|
+ ,WM_CONCAT(DISTINCT ',',suffix) AS suffix
|
|
|
+ FROM t_bucket
|
|
|
+ GROUP BY dt
|
|
|
+ ,apptype
|
|
|
+ ,abcode
|
|
|
+ ,source_type
|
|
|
+ ,layer_type
|
|
|
+)
|
|
|
+SELECT a.dt
|
|
|
+ ,a.apptype
|
|
|
+ ,a.abcode
|
|
|
+ ,a.source_type
|
|
|
+ ,a.layer_type
|
|
|
+ ,a.suffix
|
|
|
+ ,a.exp_per_dau
|
|
|
+ ,a.str_one
|
|
|
+ ,a.ros_one
|
|
|
+ ,a.str
|
|
|
+ ,a.ros
|
|
|
+ ,a.str_plus
|
|
|
+ ,a.ros_minus
|
|
|
+ ,a.bn_rov
|
|
|
+ ,a.c1_rov
|
|
|
+ ,a.cn_rov
|
|
|
+ ,a.d1_rov
|
|
|
+ ,a.dn_rov
|
|
|
+ ,a.vovh24
|
|
|
+ ,a.dau
|
|
|
+ ,a.exp
|
|
|
+ ,a.is_share
|
|
|
+ ,a.share_cnt
|
|
|
+ ,a.is_return_1
|
|
|
+ ,a.return_n_uv
|
|
|
+ ,a.viewh24
|
|
|
+ ,a.return_n_uv_noself
|
|
|
+ ,a.cn
|
|
|
+ ,a.c1
|
|
|
+ ,a.dn
|
|
|
+ ,a.d1
|
|
|
+ ,b.dau2
|
|
|
+FROM t_metrics a
|
|
|
+LEFT JOIN t_dau2 b
|
|
|
+ON a.dt = b.dt
|
|
|
+AND a.apptype = b.apptype
|
|
|
+AND a.abcode = b.abcode
|
|
|
+AND a.source_type = b.source_type
|
|
|
+AND a.layer_type = b.layer_type
|
|
|
+ORDER BY a.dt DESC,a.apptype,a.abcode,a.source_type,a.layer_type
|
|
|
+;
|
