Merge branch 'master' of git.wanmeizhensuo.com:ML/ffm-baseline

增加获取城市列表

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

@@ -34,7 +34,7 @@ object GmeiConfig extends Serializable {
     val sparkConf = new SparkConf
     sparkConf.set("spark.sql.crossJoin.enabled", "true")
     sparkConf.set("spark.debug.maxToStringFields", "100")
-    sparkConf.set("spark.sql.broadcastTimeout",  "1000")
+    sparkConf.set("spark.sql.broadcastTimeout",  "6000")
 
     if (!sparkConf.contains("spark.master")) {
       sparkConf.setMaster("local[3]")

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

@@ -13,8 +13,7 @@ object Recommendation_strategy_all {
   Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
   Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
 
-  case class Params(env: String = "dev",
-                    date: String = "2018-08-01"
+  case class Params(env: String = "dev"
                    ) extends AbstractParams[Params] with Serializable
 
   val defaultParams = Params()
@@ -24,9 +23,6 @@ object Recommendation_strategy_all {
     opt[String]("env")
       .text(s"the databases environment you used")
       .action((x, c) => c.copy(env = x))
-    opt[String] ("date")
-      .text(s"the date you used")
-      .action((x,c) => c.copy(date = x))
     note(
       """
         |For example, the following command runs this app on a tidb dataset:
@@ -54,6 +50,7 @@ object Recommendation_strategy_all {
 
       import sc.implicits._
       val stat_date = GmeiConfig.getMinusNDate(1)
+      println(stat_date)
       //println(param.date)
       val partition_date = stat_date.replace("-","")
       val decive_id_oldUser = sc.sql(

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

@@ -264,9 +264,61 @@ object NdDataInput {
       tidb_input.show()
       println(tidb_input.count())
 
+    }
+  }
+}
+
+
+
+
+object ServiceStat {
+
+  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
+  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
+
+  case class Params(env: String = "dev"
+                   ) extends AbstractParams[Params] with Serializable
+
+  val defaultParams = Params()
+
+  val parser = new OptionParser[Params]("Feed_EDA") {
+    head("WeafareStat")
+    opt[String]("env")
+      .text(s"the databases environment you used")
+      .action((x, c) => c.copy(env = x))
+    note("winter is coming")
+  }
+
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
 
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "nd_data_meigou_cid")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "eagle", tableName = "feed_diary_boost")
 
+      val result00 = sc.sql(
+        s"""
+           |select a.cl_id as device_id,
+           |COALESCE(a.params['diary_id'], a.params['business_id'], 0) as diary_id,
+           |c.level1_id as level1_id
+           |from online.tl_hdfs_maidian_view a
+           |left join online.tl_hdfs_diary_tags_view b on COALESCE(a.params['diary_id'], a.params['business_id'], 0)=b.diary_id
+           |left join online.bl_tag_hierarchy_detail c on b.tag_id=c.id
+           |where a.partition_date > "20181112"
+           |and a.action="on_click_diary_card"
+           |and a.params["page_name"]="home"
+           |and a.cl_id != "NULL"
+           |and b.partition_date="20181119"
+           |and c.partition_date="20181119"
+     """.stripMargin
+      )
+      result00.collect.foreach(println)
 
     }
   }
-}
+}
\ No newline at end of file

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

+package com.gmei
+
+import java.io.Serializable
+
+import org.apache.spark.sql.functions.udf
+import com.gmei.WeafareStat.{defaultParams, parser}
+import org.apache.spark.sql.{SaveMode, TiContext}
+import org.apache.log4j.{Level, Logger}
+import scopt.OptionParser
+import com.gmei.lib.AbstractParams
+import java.io._
+import java.text.SimpleDateFormat
+import java.util.Calendar
+
+import org.apache.spark
+
+object app_list {
+
+  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
+  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
+
+  case class Params(env: String = "dev",
+                    date: String = "2018-08-01"
+                   ) extends AbstractParams[Params] with Serializable
+
+  val defaultParams = Params()
+
+  val parser = new OptionParser[Params]("Feed_EDA") {
+    head("WeafareStat")
+    opt[String]("env")
+      .text(s"the databases environment you used")
+      .action((x, c) => c.copy(env = x))
+    opt[String] ("date")
+      .text(s"the date you used")
+      .action((x,c) => c.copy(date = x))
+    note(
+      """
+        |For example, the following command runs this app on a tidb dataset:
+        |
+        | spark-submit --class com.gmei.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
+      """.stripMargin +
+        s"|   --env ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_test", tableName = "bl_device_list")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "merge_queue_table")
+
+
+      import sc.implicits._
+      val stat_date = GmeiConfig.getMinusNDate(1)
+      println(param.date)
+      val partition_date = param.date.replace("-","")
+      println(partition_date)
+
+      //自定义udf函数，增加dataframe 列
+      val code = (arg: String) => {
+        if (arg.getClass.getName == "java.lang.String") partition_date.toInt else 0.toInt
+      }
+
+      val addCol = udf(code)
+      //以上为udf函数
+
+
+      //机构ID
+      val agency_id = sc.sql(
+        s"""
+           |SELECT DISTINCT(cl_id) as device_id
+           |FROM online.ml_hospital_spam_pv_day
+           |WHERE partition_date >= '20180402'
+           |AND partition_date <= '20181120'
+           |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 <= '20181120'
+           |AND pv_ratio >= 0.95
+         """.stripMargin
+      )
+      agency_id.createOrReplaceTempView("agency_id")
+
+
+      //获取与新氧用户重合的用户device_id
+      val app_list = sc.sql(
+        s"""
+           |select distinct(cl_id) as device_id, user_id as user_id, params['installed_app_info'] as app_list,channel
+           |from online.tl_hdfs_maidian_view ov left join agency_id
+           |on ov.cl_id = agency_id.device_id
+           |where ov.action="user_installed_all_app_info"
+           |and ov.partition_date = '${partition_date}'
+           |and agency_id.device_id is null
+           |and  ov.cl_id not in (select distinct(device_id) from blacklist)
+         """.stripMargin
+      )
+      //app_list.show()
+      import sc.implicits._
+      val rdd_df = app_list.rdd.map(x =>(x(0).toString,x(1).toString,x(2).toString,x(3).toString))
+        .filter(x => x._3.contains("新氧美容")).map(x => (x._1,x._2,x._3,x._4)).collect().toList.toDF("device_id","user_id","app_list","channel")
+      rdd_df.show()
+      //rdd_df.withColumn("stat_date",addCol(rdd_df("device_id")))
+      rdd_df.createOrReplaceTempView("device_id")
+
+      val temp = sc.sql(
+        s"""
+           |select *
+           |from device_id
+         """.stripMargin
+      )
+      val tempp=temp.withColumn("stat_date",addCol(temp("device_id")))
+
+      tempp.show()
+
+      GmeiConfig.writeToJDBCTable(tempp, "device_id_coincidence", SaveMode.Append)
+
+
+//所有获得应用列表的用户device_id
+      val app_list_all = sc.sql(
+        s"""
+           |select distinct(cl_id) as device_id, user_id as user_id,params['installed_app_info'] as app_list,channel
+           |from online.tl_hdfs_maidian_view ov left join agency_id
+           |on ov.cl_id = agency_id.device_id
+           |where action="user_installed_all_app_info"
+           |and agency_id.device_id is null
+           |and ov.partition_date = '${partition_date}'
+           |and ov.cl_id not in (select distinct(device_id) from blacklist)
+         """.stripMargin
+      )
+      val tempp_list=app_list_all.withColumn("stat_date",addCol(app_list_all("device_id")))
+
+      GmeiConfig.writeToJDBCTable(tempp_list, "device_id_applist", SaveMode.Append)
+
+
+    }
+
+
+  }
+
+}
+
+
+
+
+//以下object进行数据统计分析
+object coincidence_xinyang {
+
+  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
+  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
+
+  case class Params(env: String = "dev",
+                    date: String = "2018-08-01"
+                   ) extends AbstractParams[Params] with Serializable
+
+  val defaultParams = Params()
+
+  val parser = new OptionParser[Params]("Feed_EDA") {
+    head("WeafareStat")
+    opt[String]("env")
+      .text(s"the databases environment you used")
+      .action((x, c) => c.copy(env = x))
+    opt[String] ("date")
+      .text(s"the date you used")
+      .action((x,c) => c.copy(date = x))
+    note(
+      """
+        |For example, the following command runs this app on a tidb dataset:
+        |
+        | spark-submit --class com.gmei.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
+      """.stripMargin +
+        s"|   --env ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "device_id_applist")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "device_id_coincidence")
+
+
+      //println(param.date)
+      //val partition_date = param.date.replace("-","")
+      //println(partition_date)
+
+      //获取昨天的日期
+      def getYesterDay():String={
+        var  dateFormat:SimpleDateFormat = new SimpleDateFormat("yyyy-MM-dd")
+        var cal:Calendar=Calendar.getInstance()
+        cal.add(Calendar.DATE,-1)
+        var yesterday=dateFormat.format(cal.getTime())
+        yesterday
+      }
+      val yesterday=getYesterDay()
+      println(yesterday)
+      //获取一周前的日期
+      def getWeekDay():String={
+        var  dateFormat:SimpleDateFormat = new SimpleDateFormat("yyyy-MM-dd")
+        var cal:Calendar=Calendar.getInstance()
+        cal.add(Calendar.DATE,-7)
+        var yesterday=dateFormat.format(cal.getTime())
+        yesterday
+      }
+      val pre_weekday=getWeekDay()
+      println(pre_weekday)
+      //获取一个月前的日期
+      def getMonthDay():String={
+        var  dateFormat:SimpleDateFormat = new SimpleDateFormat("yyyy-MM-dd")
+        var cal:Calendar=Calendar.getInstance()
+        cal.add(Calendar.DATE,-30)
+        var yesterday=dateFormat.format(cal.getTime())
+        yesterday
+      }
+      val pre_monthday = getMonthDay()
+      println(pre_monthday)
+
+
+      //获取每日活跃用户中与新氧重合用户占比
+      //1.每日活跃中与新氧重合用户数
+      val yesterday_data = yesterday.replace("-","")
+      val yesterday_coincidence = sc.sql(
+        s"""
+           |select '${yesterday_data}' as stat_date,count(distinct(device_id)) as yesterday_coincidence_num
+           |from device_id_coincidence
+           |where stat_date = '${yesterday_data}'
+         """.stripMargin
+      )
+      //2.获得应用列表的每日活跃总用户数
+      val yesterday_expoure_num = sc.sql(
+        s"""
+           |select '${yesterday_data}' as stat_date,count(distinct(device_id)) as yesterday_expoure_num
+           |from device_id_applist
+           |where stat_date = '${yesterday_data}'
+         """.stripMargin
+      )
+
+
+      //获取每周活跃用户中与新氧重合用户占比
+      //1.每周活跃中与新氧重合用户数
+      val week_day = pre_weekday.replace("-","")
+      val week_coincidence = sc.sql(
+        s"""
+           |select '${yesterday_data}' as stat_date,count(distinct(device_id)) as week_coincidence_num
+           |from device_id_coincidence
+           |where stat_date >= '${week_day}'
+         """.stripMargin
+      )
+      //2.获得应用列表的每周活跃总用户
+      val week_expoure_num = sc.sql(
+        s"""
+           |select '${yesterday_data}' as stat_date,count(distinct(device_id)) as week_expoure_num
+           |from device_id_applist
+           |where stat_date >= '${week_day}'
+         """.stripMargin
+      )
+
+ /*     //获取每月活跃用户中与新氧用户重合用户占比
+      //1.0 每月活跃中与新氧用户重合用户数
+      val month_day=pre_monthday.replace("-","")
+      val month_coincidence = sc.sql(
+        s"""
+           |select '${data}' as stat_date,count(distinct(device_id)) as month_coincidence_num
+           |from device_id_coincidence
+           |where stat_date > '${month_day}'
+         """.stripMargin
+      )
+      //2.0 获得应用列表的每月活跃总用户
+      val month_expoure_num = sc.sql(
+        s"""
+           |select '${data}' as stat_date,count(distinct(cl_id)) as month_expoure_num
+           |from online.tl_hdfs_maidian_view
+           |where partition_date >= '${month_day}'
+           |and action="user_installed_all_app_info"
+           |and cl_id not in (select device_id from bl_device_list)
+           |and cl_id not in (select device_id from blacklist)
+         """.stripMargin
+      )
+*/
+      val result = yesterday_coincidence.join(yesterday_expoure_num,"stat_date")
+          .join(week_coincidence,"stat_date")
+          .join(week_expoure_num,"stat_date")
+
+      GmeiConfig.writeToJDBCTable(result, "coincidence_xinyang", SaveMode.Append)
+
+      //获取到的应用列表用户中截止目前获得的与新氧重合的用户数计算美购情况
+      //* 重合用户的id
+      val coincidence_id = sc.sql(
+        s"""
+           |select distinct(device_id) as device_id
+           |from device_id_coincidence
+         """.stripMargin
+      )
+      coincidence_id.createOrReplaceTempView("coincidence_id")
+
+
+//获取应用列表的所有用户id
+      val all_id = sc.sql(
+        s"""
+           |select distinct(device_id) as device_id
+           |from device_id_applist
+         """.stripMargin
+      )
+      all_id.createOrReplaceTempView("all_id")
+
+      //* 所有获得用户列表的用户id
+      //1.重合用户的美购数
+      val meigou_coincidence_num = sc.sql(
+        s"""
+           |select count(ov.device_id) as meigou_coincidence_num
+           |from online.ml_meigou_order_detail ov left join coincidence_id
+           |on ov.device_id = coincidence_id.device_id
+           |where partition_date = '20181120'
+           |and coincidence_id.device_id is not null
+           |and  ov.pay_time  is  not  null
+           |and  ov.pay_time  >=  '2017-11-18'
+         """.stripMargin
+      )
+      meigou_coincidence_num.show()
+
+
+      //2.重合用户进行美购的用户数
+      val meigou_pay_device = sc.sql(
+        s"""
+           |select count(distinct(ov.device_id)) as meigou_coincidence_num
+           |from online.ml_meigou_order_detail ov left join coincidence_id
+           |on ov.device_id = coincidence_id.device_id
+           |where partition_date = '20181120'
+           |and coincidence_id.device_id is not null
+           |and  ov.pay_time  is  not  null
+           |and  ov.pay_time  >=  '2017-11-18'
+         """.stripMargin
+      )
+      meigou_pay_device.show()
+      //3.所有获得应用列表的用户的美购数
+      val meigou_pay_all = sc.sql(
+        s"""
+           |select count(od.device_id) as meigou_pay_device
+           |from online.ml_meigou_order_detail od  inner join all_id
+           |on od.device_id = all_id.device_id
+           |where partition_date = '20181120'
+           |and  all_id.device_id is not null
+           |and  od.pay_time  is  not  null
+           |and  od.pay_time  >=  '2017-11-18'
+         """.stripMargin
+      )
+      meigou_pay_all.show()
+
+      //4.所有获得应用列表用户进行美购的用户数
+      val meigou_pay_device_all = sc.sql(
+        s"""
+           |select count(distinct(od.device_id)) as meigou_pay_device
+           |from online.ml_meigou_order_detail od  inner join all_id
+           |on od.device_id = all_id.device_id
+           |where partition_date = '20181120'
+           |and  all_id.device_id is not null
+           |and  od.pay_time  is  not  null
+           |and  od.pay_time  >=  '2017-11-18'
+         """.stripMargin
+      )
+      meigou_pay_device_all.show()
+
+      //截止目前获得的与新氧重合的用户数咨询统计
+/*      val zixun_num_all = sc.sql(
+        s"""
+           |select count(ov.cl_id)  as zixun_num_all
+           |from online.tl_hdfs_maidian_view ov left join coincidence_id
+           |on ov.cl_id = coincidence_id.device_id
+           |where partition_date >= '20180501'
+           |and coincidence_id.device_id is not null
+           |and action = 'welfare_detail_click_message'
+         """.stripMargin
+      )
+      zixun_num_all.show()
+
+      val zixun_device_all = sc.sql(
+        s"""
+           |select count(distinct(ov.cl_id))  as zixun_num_all
+           |from online.tl_hdfs_maidian_view ov left join coincidence_id
+           |on ov.cl_id = coincidence_id.device_id
+           |where partition_date >= '20180501'
+           |and coincidence_id.device_id is not null
+           |and action = 'welfare_detail_click_message'
+         """.stripMargin
+      )
+      zixun_device_all.show()
+*/
+      val zixun_num_co = sc.sql(
+        s"""
+           |select count(ov.cl_id)  as zixun_num_all
+           |from online.tl_hdfs_maidian_view ov left join all_id
+           |on ov.cl_id = all_id.device_id
+           |where partition_date >= '20180501'
+           |and all_id.device_id is not null
+           |and action = 'welfare_detail_click_message'
+         """.stripMargin
+      )
+      zixun_num_co.show()
+
+      val zixun_num_co_dis = sc.sql(
+        s"""
+           |select count(distinct(ov.cl_id))  as zixun_num_all
+           |from online.tl_hdfs_maidian_view ov left join all_id
+           |on ov.cl_id = all_id.device_id
+           |where partition_date >= '20180501'
+           |and all_id.device_id is not null
+           |and action = 'welfare_detail_click_message'
+         """.stripMargin
+      )
+      zixun_num_co_dis.show()
+
+
+
+
+
+    }
+
+
+  }
+
+}

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

@@ -179,3 +179,174 @@ 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_ {
+
+  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
+  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
+
+  case class Params(env: String = "dev",
+                    date: String = "2018-08-01"
+                   ) extends AbstractParams[Params] with Serializable
+
+  val defaultParams = Params()
+
+  val parser = new OptionParser[Params]("Feed_EDA") {
+    head("WeafareStat")
+    opt[String]("env")
+      .text(s"the databases environment you used")
+      .action((x, c) => c.copy(env = x))
+    opt[String] ("date")
+      .text(s"the date you used")
+      .action((x,c) => c.copy(date = x))
+    note(
+      """
+        |For example, the following command runs this app on a tidb dataset:
+        |
+        | spark-submit --class com.gmei.WeafareStat ./target/scala-2.11/feededa-assembly-0.1.jar \
+      """.stripMargin +
+        s"|   --env ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      import sc.implicits._
+      //val stat_date = GmeiConfig.getMinusNDate(1)
+      //println(param.date)
+      val partition_date = param.date.replace("-","")
+      val devicee_id_oldUser = sc.sql(
+        s"""
+           |select distinct(device_id) as device_id
+           |from online.ml_device_day_active_status
+           |where active_type = '4'
+           |and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
+           |        ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
+           |        ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
+           |        ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
+           |        ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
+           |        ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
+           |        ,'promotion_shike','promotion_julang_jl03')
+           |and partition_date ='${partition_date}'
+         """.stripMargin
+      )
+      devicee_id_oldUser.show()
+      devicee_id_oldUser.createOrReplaceTempView("device_id_old")
+
+      //device_id尾号1有点击用户日记本点击数
+      val clk_active_1 = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(jd.cid_id) as clk_active_1
+           |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$$'
+           |and jd.device_id not in (select device_id from bl_device_list)
+           |and jd.device_id not in (select device_id from blacklist)
+           |and jd.stat_date ='${param.date}'
+         """.stripMargin
+      )
+
+      //device_id尾号1有点击用户日记本曝光数
+      val imp_active_1 = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(je.cid_id) as imp_active_1
+           |from data_feed_exposure je inner join device_id_old
+           |on je.device_id = device_id_old.device_id
+           |where je.cid_type = 'diary'
+           |and je.device_id in (select distinct(device_id) from data_feed_click where device_id regexp '1$$' and stat_date = '${param.date}')
+           |and je.device_id not in (select device_id from bl_device_list)
+           |and je.device_id not in (select device_id from blacklist)
+           |and je.stat_date ='${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 ='${param.date}'
+            """.stripMargin
+      )
+
+      //所有有点击用户日记本点击数
+      val clk_active_all = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(jd.cid_id) as clk_active_all
+           |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 not in (select device_id from bl_device_list)
+           |and jd.device_id not in (select device_id from blacklist)
+           |and jd.stat_date ='${param.date}'
+                  """.stripMargin
+      )
+
+      //所有有点击用户日记本曝光数
+      val imp_active_all = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date, count(je.cid_id) as imp_active_all
+           |from data_feed_exposure je inner join device_id_old
+           |on je.device_id = device_id_old.device_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(
+        s"""
+           |select '${param.date}' as stat_date,count(distinct(device_id)) as clk_diary_device_cover
+           |from merge_queue_table
+           |where device_id in (select distinct(device_id) from data_feed_click where stat_date = '${param.date}')
+                  """.stripMargin
+      )
+
+      //策略命中用户总数
+      val device_all_cover = sc.sql(
+        s"""
+           |select '${param.date}' as stat_date,count(distinct(device_id)) as device_all_cover
+           |from merge_queue_table
+                  """.stripMargin
+      )
+
+
+
+      val result = 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")
+      result.show()
+
+      GmeiConfig.writeToJDBCTable(result, "strategy_other", SaveMode.Append)
+
+
+    }
+
+
+  }
+
+}
+

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

@@ -54,7 +54,6 @@ object testt {
              |from online.tl_hdfs_maidian_view
              |where action="page_view"
              |and params["page_name"]="diary_detail"
-             |and (params["out"]-params["in"])<7200
              |and partition_date >='20180901'
          """.stripMargin
         )
@@ -71,9 +70,6 @@ object testt {
 
       }
 
-
-
-
     }