增加统计数据

eda/feededa/src/main/scala/com/gmei/Recommendation_strategy_all.scala

@@ -154,6 +154,40 @@ object Recommendation_strategy_all {
            |and je.stat_date ='${stat_date}'
          """.stripMargin
       )
+      //策略覆盖用户数device_num_cover
+      val device_num_cover = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date,count(distinct(device_id)) as device_num_cover
+           |from merge_queue_table
+         """.stripMargin
+      )
+
+      //尾号1活跃用户数device_num_1_hit
+      val device_num_1_hit = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(distinct(je.device_id)) as device_num_1_hit
+           |from data_feed_exposure je inner join device_id_old
+           |on je.device_id = device_id_old.decive_id
+           |where je.cid_type = 'diary'
+           |and je.device_id regexp'1$$'
+           |and je.device_id not in (select device_id from bl_device_list)
+           |and je.device_id not in (select device_id from blacklist)
+           |and je.stat_date ='${stat_date}'
+         """.stripMargin
+      )
+
+      //策略命中用户数device_num_hit
+      val device_num_hit = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(distinct(je.device_id)) as device_num_hit
+           |from data_feed_exposure je inner join device_id_cover_older
+           |on je.device_id = device_id_cover_older.device_id
+           |where je.cid_type = 'diary'
+           |and je.device_id not in (select device_id from bl_device_list)
+           |and je.device_id not in (select device_id from blacklist)
+           |and je.stat_date ='${stat_date}'
+         """.stripMargin
+      )
 
 
 
@@ -163,6 +197,9 @@ object Recommendation_strategy_all {
           .join(imp_count_oldUser_all,"stat_date")
           .join(clk_count_oldUser_Cover,"stat_date")
           .join(imp_count_oldUser_Cover,"stat_date")
+          .join(device_num_cover,"stat_date")
+          .join(device_num_1_hit,"stat_date")
+          .join(device_num_hit,"stat_date")
       result1.show()
 
       GmeiConfig.writeToJDBCTable(result1, "Recommendation_strategy_temp", SaveMode.Append)
@@ -269,6 +306,10 @@ object Recommendation_strategy_all {
 
 
 
+
+
+
+
     }
 
 

eda/feededa/src/main/scala/com/gmei/strategy_other.scala

@@ -36,7 +36,7 @@ object strategy_other {
         s"|   --env ${defaultParams.env}"
     )
   }
-
+//统计每天新用户的点击率
   def main(args: Array[String]): Unit = {
     parser.parse(args, defaultParams).map { param =>
       GmeiConfig.setup(param.env)
@@ -56,11 +56,11 @@ object strategy_other {
       //val stat_date = GmeiConfig.getMinusNDate(1)
       //println(param.date)
       val partition_date = param.date.replace("-","")
-      val devicee_id_oldUser = sc.sql(
+      val devicee_id_newUser = sc.sql(
         s"""
            |select distinct(device_id) as device_id
            |from online.ml_device_day_active_status
-           |where active_type = '4'
+           |where active_type != '4'
            |and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
            |        ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
            |        ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
@@ -71,15 +71,14 @@ object strategy_other {
            |and partition_date ='${partition_date}'
          """.stripMargin
       )
-      devicee_id_oldUser.show()
-      devicee_id_oldUser.createOrReplaceTempView("device_id_old")
+      devicee_id_newUser.show()
+      devicee_id_newUser.createOrReplaceTempView("device_id_new")
 
-//device_id尾号1有点击用户日记本点击数
-      val clk_active_1 = sc.sql(
+      val clk_count_oldUser_Contrast = sc.sql(
         s"""
-           |select '${param.date}' as stat_date, count(jd.cid_id) as clk_active_1
+           |select '${param.date}' as stat_date, count(cid_id) as clk_count_oldUser_Contrast
            |from data_feed_click jd inner join device_id_old
-           |on jd.device_id = device_id_old.device_id
+           |on jd.device_id = device_id_old.decive_id
            |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
            |and jd.device_id regexp'1$$'
            |and jd.device_id not in (select device_id from bl_device_list)
@@ -88,40 +87,24 @@ object strategy_other {
          """.stripMargin
       )
 
-      //device_id尾号1有点击用户日记本曝光数
-      val imp_active_1 = sc.sql(
+      val imp_count_oldUser_Contrast = sc.sql(
         s"""
-           |select '${param.date}' as stat_date, count(je.cid_id) as imp_active_1
+           |select '${param.date}' as stat_date, count(cid_id) as imp_count_oldUser_Contrast
            |from data_feed_exposure je inner join device_id_old
-           |on je.device_id = device_id_old.device_id
+           |on je.device_id = device_id_old.decive_id
            |where je.cid_type = 'diary'
-           |and je.device_id in (select distinct(device_id) from data_feed_click where device_id regexp '1$$' and stat_date = '${param.date}')
+           |and je.device_id regexp'1$$'
            |and je.device_id not in (select device_id from bl_device_list)
            |and je.device_id not in (select device_id from blacklist)
            |and je.stat_date ='${param.date}'
          """.stripMargin
       )
 
-      //device_id尾号1点击日记本用户数
-      val clk_diary_device = sc.sql(
-           s"""
-              |select '${param.date}' as stat_date, count(distinct(jd.device_id)) as clk_diary_device
-              |from data_feed_click jd inner join device_id_old
-              |on jd.device_id = device_id_old.device_id
-              |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
-              |and jd.device_id regexp'1$$'
-              |and jd.device_id not in (select device_id from bl_device_list)
-              |and jd.device_id not in (select device_id from blacklist)
-              |and jd.stat_date ='${param.date}'
-            """.stripMargin
-         )
-
-               //所有有点击用户日记本点击数
-               val clk_active_all = sc.sql(
+      val clk_count_oldUser_all = sc.sql(
         s"""
-                    |select '${param.date}' as stat_date, count(jd.cid_id) as clk_active_all
+           |select '${param.date}' as stat_date, count(cid_id) as clk_count_oldUser_all
            |from data_feed_click jd inner join device_id_old
-                    |on jd.device_id = device_id_old.device_id
+           |on jd.device_id = device_id_old.decive_id
            |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
            |and jd.device_id not in (select device_id from bl_device_list)
            |and jd.device_id not in (select device_id from blacklist)
@@ -129,48 +112,63 @@ object strategy_other {
          """.stripMargin
       )
 
-         //所有有点击用户日记本曝光数
-               val imp_active_all = sc.sql(
+      val imp_count_oldUser_all = sc.sql(
         s"""
-                    |select '${param.date}' as stat_date, count(je.cid_id) as imp_active_all
+           |select '${param.date}' as stat_date, count(cid_id) as imp_count_oldUser_all
            |from data_feed_exposure je inner join device_id_old
-                    |on je.device_id = device_id_old.device_id
+           |on je.device_id = device_id_old.decive_id
            |where je.cid_type = 'diary'
-                    |and je.device_id in (select distinct(device_id) from data_feed_click where stat_date = '${param.date}')
            |and je.device_id not in (select device_id from bl_device_list)
            |and je.device_id not in (select device_id from blacklist)
            |and je.stat_date ='${param.date}'
          """.stripMargin
       )
 
-               //策略命中用户点击日记本用户数
-               val clk_diary_device_cover = sc.sql(
+      //获取策略命中用户device_id
+      val device_id_cover = sc.sql(
         s"""
-                    |select '${param.date}' as stat_date,count(distinct(device_id)) as clk_diary_device_cover
+           |select distinct(device_id) as device_id
            |from merge_queue_table
-                    |where device_id in (select distinct(device_id) from data_feed_click where stat_date = '${param.date}')
          """.stripMargin
       )
+      device_id_cover.createOrReplaceTempView("device_id_cover_older")
+
 
-               //策略命中用户总数
-               val device_all_cover = sc.sql(
+      val clk_count_oldUser_Cover = sc.sql(
         s"""
-                    |select '${param.date}' as stat_date,count(distinct(device_id)) as device_all_cover
-                    |from merge_queue_table
+           |select '${param.date}' as stat_date, count(cid_id) as clk_count_oldUser_Cover
+           |from data_feed_click jd inner join device_id_cover_older
+           |on jd.device_id = device_id_cover_older.device_id
+           |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+           |and jd.device_id not in (select device_id from bl_device_list)
+           |and jd.device_id not in (select device_id from blacklist)
+           |and jd.stat_date ='${param.date}'
          """.stripMargin
       )
 
+      val imp_count_oldUser_Cover = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(cid_id) as imp_count_oldUser_Cover
+           |from data_feed_exposure je inner join device_id_cover_older
+           |on je.device_id = device_id_cover_older.device_id
+           |where je.cid_type = 'diary'
+           |and je.device_id not in (select device_id from bl_device_list)
+           |and je.device_id not in (select device_id from blacklist)
+           |and je.stat_date ='${param.date}'
+         """.stripMargin
+      )
+
+
 
 
-      val result2 = clk_active_1.join(imp_active_1,"stat_date")
-        .join(clk_active_all,"stat_date")
-        .join(imp_active_all,"stat_date")
-        .join(clk_diary_device,"stat_date")
-        .join(clk_diary_device_cover,"stat_date")
-          .join(device_all_cover,"stat_date")
-      result2.show()
+      val result1 = clk_count_oldUser_Contrast.join(imp_count_oldUser_Contrast,"stat_date")
+        .join(clk_count_oldUser_all,"stat_date")
+        .join(imp_count_oldUser_all,"stat_date")
+        .join(clk_count_oldUser_Cover,"stat_date")
+        .join(imp_count_oldUser_Cover,"stat_date")
+      result1.show()
 
-      GmeiConfig.writeToJDBCTable(result2, "strategy_other", SaveMode.Append)
+      GmeiConfig.writeToJDBCTable(result1, "Recommendation_strategy_temp", SaveMode.Append)
 
 
     }