修改统计参数

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

@@ -194,6 +194,18 @@ object coincidence_xinyang {
       val pre_monthday = getMonthDay()
       println(pre_monthday)
 
+      //获取截止目前获得应用列表的用户的device_id
+      val all_device_id = sc.sql(
+        s"""
+           |select distinct(cl_id) as device_id
+           |from online.tl_hdfs_maidian_view
+           |where action="user_installed_all_app_info"
+           |and partition_date >= '20181114'
+           |and cl_id not in (select device_id from bl_device_list)
+           |and cl_id not in (select device_id from blacklist)
+         """.stripMargin
+      )
+      all_device_id.createOrReplaceTempView("all_device_id")
 
 
       //获取每日活跃用户中与新氧重合用户占比
@@ -206,16 +218,19 @@ object coincidence_xinyang {
            |where stat_date = '${data}'
          """.stripMargin
       )
-      //2.每日活跃总用户数(采用曝光计算)
+      //2.获得应用列表的每日活跃总用户数
       val yesterday_expoure_num = sc.sql(
         s"""
-           |select '${data}' as stat_date,count(distinct(device_id)) as yesterday_expoure_num
-           |from data_feed_exposure
-           |where stat_date = '${yesterday}'
-           |and device_type !='App Store'
+           |select '${data}' as stat_date,count(distinct(cl_id)) as yesterday_expoure_num
+           |from online.tl_hdfs_maidian_view
+           |where partition_date = '${data}'
+           |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
       )
 
+
       //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("-","")
@@ -223,16 +238,18 @@ object coincidence_xinyang {
         s"""
            |select '${data}' as stat_date,count(distinct(device_id)) as week_coincidence_num
            |from device_id_coincidence
-           |where stat_date > '${week_day}'
+           |where stat_date >= '${week_day}'
          """.stripMargin
       )
-      //2.每周活跃总用户(采用曝光计算)
+      //2.获得应用列表的每周活跃总用户
       val week_expoure_num = sc.sql(
         s"""
-           |select '${data}' as stat_date,count(distinct(device_id)) as week_expoure_num
-           |from data_feed_exposure
-           |where stat_date > '${pre_weekday}'
-           |and device_type !='App Store'
+           |select '${data}' as stat_date,count(distinct(cl_id)) as week_expoure_num
+           |from online.tl_hdfs_maidian_view
+           |where partition_date >= '${week_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
       )
 
@@ -246,12 +263,15 @@ object coincidence_xinyang {
            |where stat_date > '${month_day}'
          """.stripMargin
       )
-      //2.0 每月活跃总用户（采用曝光计算）
+      //2.0 获得应用列表的每月活跃总用户
       val month_expoure_num = sc.sql(
         s"""
-           |select '${data}' as stat_date,count(distinct(device_id)) as month_expoure_num
-           |from data_feed_exposure
-           |where stat_date > '${pre_monthday}'
+           |select '${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
       )
 
@@ -263,13 +283,13 @@ object coincidence_xinyang {
 
       GmeiConfig.writeToJDBCTable(result, "coincidence_xinyang", SaveMode.Append)
 
-      //截止目前获得的与新氧重合的用户数计算美购情况
+      //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
       //1.重合用户的美购数
       val meigou_coincidence_num = sc.sql(
         s"""
            |select count(service_id) as meigou_coincidence_num
            |from online.ml_meigou_order_detail
-           |where partition_date = '20181118'
+           |where partition_date = '20181120'
            |and  pay_time  is  not  null
            |and  pay_time  >=  '2017-11-18'
            |and device_id in (select distinct(device_id) from device_id_coincidence)
@@ -283,37 +303,35 @@ object coincidence_xinyang {
         s"""
            |select count(DISTINCT(device_id)) as meigou_pay_device
            |from online.ml_meigou_order_detail
-           |where partition_date = '20181118'
+           |where partition_date = '20181120'
            |and  pay_time  is  not  null
            |and  pay_time  >=  '2017-11-18'
            |and device_id in (select distinct(device_id) from device_id_coincidence)
          """.stripMargin
       )
       meigou_pay_device.show()
-      //3.所有用户的美购数
+      //3.获得应用列表的用户的美购数
       val meigou_pay_all = sc.sql(
         s"""
            |select count(device_id) as meigou_pay_device
-           |from online.ml_meigou_order_detail
-           |where partition_date = '20181118'
+           |from online.ml_meigou_order_detail od  inner join all_device_id
+           |on od.device_id=all_device_id.device_id
+           |where partition_date = '20181120'
            |and  pay_time  is  not  null
            |and  pay_time  >=  '2017-11-18'
-           |and device_id not in (select device_id from bl_device_list)
-           |and device_id not in (select device_id from blacklist)
          """.stripMargin
       )
       meigou_pay_all.show()
 
-      //4.所有进行美购的用户数
+      //4.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(device_id)) as meigou_pay_device
-           |from online.ml_meigou_order_detail
-           |where partition_date = '20181118'
+           |select count(distinct(device_id)) as meigou_pay_device
+           |from online.ml_meigou_order_detail od  inner join all_device_id
+           |on od.device_id=all_device_id.device_id
+           |where partition_date = '20181120'
            |and  pay_time  is  not  null
            |and  pay_time  >=  '2017-11-18'
-           |and device_id not in (select device_id from bl_device_list)
-           |and device_id not in (select device_id from blacklist)
          """.stripMargin
       )
       meigou_pay_device_all.show()
@@ -322,23 +340,21 @@ object coincidence_xinyang {
       val zixun_num_all = sc.sql(
         s"""
            |select count(cl_id)  as zixun_num_all
-           |from online.tl_hdfs_maidian_view
-           |where partition_date > '20180501'
+           |from online.tl_hdfs_maidian_view ov inner join all_device_id
+           |on ov.cl_id = all_device_id.device_id
+           |where partition_date >= '20180501'
            |and action = 'welfare_detail_click_message'
-           |and cl_id not in (select device_id from bl_device_list)
-           |and cl_id not in (select device_id from blacklist)
          """.stripMargin
       )
       zixun_num_all.show()
 
       val zixun_device_all = sc.sql(
         s"""
-           |select count(distinct(cl_id)) zixun_device_all
-           |from online.tl_hdfs_maidian_view
-           |where partition_date > '20180501'
+           |select count(distinct(cl_id))  as zixun_num_all
+           |from online.tl_hdfs_maidian_view ov inner join all_device_id
+           |on ov.cl_id = all_device_id.device_id
+           |where partition_date >= '20180501'
            |and action = 'welfare_detail_click_message'
-           |and cl_id not in (select device_id from bl_device_list)
-           |and cl_id not in (select device_id from blacklist)
          """.stripMargin
       )
       zixun_device_all.show()
@@ -347,7 +363,7 @@ object coincidence_xinyang {
         s"""
            |select count(cl_id)  as zixun_num_co
            |from online.tl_hdfs_maidian_view
-           |where partition_date > '20180501'
+           |where partition_date >= '20180501'
            |and action = 'welfare_detail_click_message'
            |and cl_id in (select distinct(device_id) from device_id_coincidence)
          """.stripMargin
@@ -358,7 +374,7 @@ object coincidence_xinyang {
         s"""
            |select count(distinct(cl_id))  as zixun_num_co_dis
            |from online.tl_hdfs_maidian_view
-           |where partition_date > '20180501'
+           |where partition_date >= '20180501'
            |and action = 'welfare_detail_click_message'
            |and cl_id in (select distinct(device_id) from device_id_coincidence)
          """.stripMargin

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

@@ -179,3 +179,183 @@ 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 ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_test", tableName = "bl_device_list")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "merge_queue_table")
+
+
+      import sc.implicits._
+      //val stat_date = GmeiConfig.getMinusNDate(1)
+      //println(param.date)
+      val partition_date = param.date.replace("-","")
+      val devicee_id_oldUser = sc.sql(
+        s"""
+           |select distinct(device_id) as device_id
+           |from online.ml_device_day_active_status
+           |where active_type = '4'
+           |and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
+           |        ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
+           |        ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
+           |        ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
+           |        ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
+           |        ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
+           |        ,'promotion_shike','promotion_julang_jl03')
+           |and partition_date ='${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)
+
+
+    }
+
+
+  }
+
+}
+