合并统计文件

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

@@ -188,10 +188,6 @@ object Recommendation_strategy_all {
            |and je.stat_date ='${stat_date}'
          """.stripMargin
       )
-
-
-
-
       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")
@@ -291,8 +287,6 @@ object Recommendation_strategy_all {
                   """.stripMargin
       )
 
-
-
       val result2 = clk_active_1.join(imp_active_1,"stat_date")
         .join(clk_active_all,"stat_date")
         .join(imp_active_all,"stat_date")
@@ -308,6 +302,83 @@ object Recommendation_strategy_all {
 
 
 
+//统计新用户点击率
+      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'
+           |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')
+           |and partition_date ='${partition_date}'
+         """.stripMargin
+      )
+      devicee_id_newUser.show()
+      devicee_id_newUser.createOrReplaceTempView("device_id_new")
+
+      val clk_count_newUser_Contrast = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(cid_id) as clk_count_newUser_Contrast
+           |from data_feed_click jd inner join device_id_new
+           |on jd.device_id = device_id_new.device_id
+           |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+           |and jd.device_id regexp'1$$'
+           |and jd.device_id not in (select device_id from blacklist)
+           |and jd.stat_date ='${stat_date}'
+         """.stripMargin
+      )
+
+      val imp_count_newUser_Contrast = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_newUser_Contrast
+           |from data_feed_exposure je inner join device_id_new
+           |on je.device_id = device_id_new.device_id
+           |where je.cid_type = 'diary'
+           |and je.device_id regexp'1$$'
+           |and je.device_id not in (select device_id from blacklist)
+           |and je.stat_date ='${stat_date}'
+         """.stripMargin
+      )
+
+      val clk_count_newUser_all = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(cid_id) as clk_count_newUser_all
+           |from data_feed_click jd inner join device_id_new
+           |on jd.device_id = device_id_new.device_id
+           |where  (jd.cid_type = 'diary' or jd.cid_type = 'diary_video')
+           |and jd.device_id not in (select device_id from blacklist)
+           |and jd.stat_date ='${stat_date}'
+         """.stripMargin
+      )
+
+      val imp_count_newUser_all = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date, count(cid_id) as imp_count_newUser_all
+           |from data_feed_exposure je inner join device_id_new
+           |on je.device_id = device_id_new.device_id
+           |where je.cid_type = 'diary'
+           |and je.device_id not in (select device_id from blacklist)
+           |and je.stat_date ='${stat_date}'
+         """.stripMargin
+      )
+
+      val result3 = clk_count_newUser_Contrast.join(imp_count_newUser_Contrast,"stat_date")
+        .join(clk_count_newUser_all,"stat_date")
+        .join(imp_count_newUser_all,"stat_date")
+      result3.show()
+
+      GmeiConfig.writeToJDBCTable(result3, "Recommendation_strategy_newUser", SaveMode.Append)
+
+
+
+
+
+
 
 
     }

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

@@ -139,10 +139,8 @@ object strategy_other {
 
 
 //下边内容开始分析统计推荐系统评价指标
-//使用信息熵描述推荐系统对长尾优质物品(日记本)的挖掘能力
-//使用基尼系数描述推荐系统对日记本推荐是否具有马太效应
 
-object evaluation_indicator {
+object diary_exposure {
 
   Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
   Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
@@ -176,21 +174,67 @@ object evaluation_indicator {
       GmeiConfig.setup(param.env)
       val spark_env = GmeiConfig.getSparkSession()
       val sc = spark_env._2
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "mimas_prod", tableName = "api_diary_tags")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+      ti.tidbMapTable(dbName = "zhengxing", tableName = "api_tag")
 
-      import sc.implicits._
-      //val stat_date = GmeiConfig.getMinusNDate(1)
-      //println(param.date)
-      val partition_date = param.date.replace("-","")
-      val diary_id = sc.sql(
+      val stat_date = GmeiConfig.getMinusNDate(1)
+
+      val temp1 = sc.sql(
+        s"""
+           |select diary_id,tag_id
+           |from api_diary_tags
+         """.stripMargin
+      )
+      temp1.createOrReplaceTempView("temp1")
+
+      val temp2 = sc.sql(
         s"""
-           |select native_queue as diary_id
-           |from doris_prod.device_diary_queue
+           |select distinct(temp1.diary_id) as diary_id,a.name as city
+           |from api_tag a left join temp1
+           |on a.id = temp1.tag_id
+           |where a.tag_type = 4
          """.stripMargin
       )
-      diary_id.show()
+      temp2.createOrReplaceTempView("temp2")
+
+      val exposure_city = sc.sql(
+        s"""
+           |select temp2.diary_id as diary_id,count(a.cid_id) as imp_num,temp2.city as city
+           |from data_feed_exposure a left join temp2
+           |on a.cid_id = temp2.diary_id
+           |where a.stat_date='${stat_date}'
+           |and temp2.diary_id is not null
+         """.stripMargin
+      )
+      exposure_city.createOrReplaceTempView("exposure_city")
+
+      val city_exposure = sc.sql(
+        s"""
+           |select count(imp_num) as num,city
+           |from exposure_city
+           |where group by city order by num
+         """.stripMargin
+      )
+      city_exposure.show(20)
+      city_exposure.createOrReplaceTempView("city_exposure")
+
+      val final_count = sc.sql(
+        s"""
+           |select city,num/count(num)
+           |from city_exposure
+         """.stripMargin
+      )
+      final_count.show()
+      val temp = final_count.collect()
+      for (i <- 0 until temp.length ) {
+        println(temp(i))
+      }
 
 
-      GmeiConfig.writeToJDBCTable(diary_id, "dairy_id_queue", SaveMode.Append)
+      //GmeiConfig.writeToJDBCTable(diary_id, "dairy_id_queue", SaveMode.Append)
 
 
     }