拆分新老用户重复曝光指标

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

@@ -499,4 +499,5 @@ object CTR_precise {
 
   }
 
-}
\ No newline at end of file
+}
+

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

@@ -223,27 +223,110 @@ object Repeated_content_recommendation {
       val partition_date = stat_date.replace("-","")
 
 
-      val exp_diary = sc.sql(
+
+      val agency_id = sc.sql(
         s"""
-           |select concat_ws('|',device_id,cid_id)
-           |from data_feed_exposure
-           |where cid_type = 'diary'
-           |and device_id not in (select device_id from blacklist)
-           |and stat_date ='${stat_date}'
+           |SELECT DISTINCT(cl_id) as device_id
+           |FROM online.ml_hospital_spam_pv_day
+           |WHERE partition_date >= '20180402'
+           |AND partition_date <= '${partition_date}'
+           |AND pv_ratio >= 0.95
+           |UNION ALL
+           |SELECT DISTINCT(cl_id) as device_id
+           |FROM online.ml_hospital_spam_pv_month
+           |WHERE partition_date >= '20171101'
+           |AND partition_date <= '${partition_date}'
+           |AND pv_ratio >= 0.95
+           |UNION ALL
+           |select distinct(device_id)
+           |from blacklist
+         """.stripMargin
+      )
+      agency_id.createOrReplaceTempView("agency_id")
+
+
+
+      val device_id_oldUser = sc.sql(
+        s"""
+           |select distinct(om.device_id) as device_id
+           |from online.ml_device_day_active_status om left join agency_id
+           |on om.device_id = agency_id.device_id
+           |where om.active_type = '4'
+           |and om.first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
+           |    ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
+           |    ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
+           |    ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
+           |    ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
+           |    ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
+           |    ,'promotion_shike','promotion_julang_jl03','','unknown')
+           |and om.partition_date ='${partition_date}'
+           |and agency_id.device_id is null
+         """.stripMargin
+      )
+      device_id_oldUser.createOrReplaceTempView("device_id_old")
+
+
+      val device_id_newUser = sc.sql(
+        s"""
+           |select distinct(om.device_id) as device_id
+           |from online.ml_device_day_active_status om left join agency_id
+           |on om.device_id = agency_id.device_id
+           |where om.active_type != '4'
+           |and om.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','','unknown')
+           |and om.partition_date ='${partition_date}'
+           |and agency_id.device_id is null
+         """.stripMargin
+      )
+      device_id_newUser.createOrReplaceTempView("device_id_new")
+
+
+
+      val exp_diary_new = sc.sql(
+        s"""
+           |select concat_ws('|',de.device_id,de.cid_id)
+           |from data_feed_exposure  de inner join device_id_new
+           |on de.device_id=device_id_new.device_id
+           |where de.cid_type = 'diary'
+           |and de.stat_date ='${stat_date}'
          """.stripMargin
       )
-      exp_diary.show()
-      val get_result =exp_diary.rdd.map((_, 1)).reduceByKey(_ + _)
+      val get_result_new =exp_diary_new.rdd.map((_, 1)).reduceByKey(_ + _)
               .sortBy(_._2,false)
 
-      val more_than2=get_result.filter(_._2 >=2).map(_._2).reduce((x,y)=>x+y)
-      println(more_than2)
-      val all =get_result.map(_._2).reduce((x,y)=>x+y)
-      println(all)
-      val repeated_rate= more_than2 / all.toDouble
-      println(repeated_rate)
-      val test=List((stat_date,repeated_rate))
-      val df = sc.createDataFrame(test)
+      val more_than2_new=get_result_new.filter(_._2 >=2).map(_._2).reduce((x,y)=>x+y)
+      println(more_than2_new)
+      val all_new =get_result_new.map(_._2).reduce((x,y)=>x+y)
+      println(all_new)
+      val repeated_rate_new= more_than2_new / all_new.toDouble
+      println(repeated_rate_new)
+
+      val exp_diary_old = sc.sql(
+        s"""
+           |select concat_ws('|',de.device_id,de.cid_id)
+           |from data_feed_exposure de inner join device_id_old
+           |where de.cid_type = 'diary'
+           |and de.stat_date ='${stat_date}'
+         """.stripMargin
+      )
+      val get_result_old =exp_diary_old.rdd.map((_, 1)).reduceByKey(_ + _)
+        .sortBy(_._2,false)
+
+      val more_than2_old=get_result_old.filter(_._2 >=2).map(_._2).reduce((x,y)=>x+y)
+      println(more_than2_old)
+      val all_old =get_result_old.map(_._2).reduce((x,y)=>x+y)
+      println(all_old)
+      val repeated_rate_old= more_than2_old / all_old.toDouble
+      println(repeated_rate_old)
+
+
+      val result=List((stat_date,more_than2_new,all_new,more_than2_old,all_old))
+      val df = sc.createDataFrame(result).toDF("stat_date","new_rep_count","new_imp_all","old_rep_count","old_imp_all")
 
       GmeiConfig.writeToJDBCTable(df, table = "Repeated_evaluation_indicator", SaveMode.Append)
 

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

@@ -408,6 +408,11 @@ object testt {
 
 
 
+
+
+
+
+
 object diary_clk_card {
 
   Logger.getLogger("org.apache.spark").setLevel(Level.WARN)