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

把esmm训练集改成train_data

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

@@ -312,7 +312,7 @@ object Repeated_content_recommendation_moreday {
 
       val now= new Date()
       val dateFormat = new SimpleDateFormat("yyyy-MM-dd")
-      val date = dateFormat.format(now.getTime - 86400000L * 15)
+      val date = dateFormat.format(now.getTime - 86400000L * 8)
       val yesterday=dateFormat.format(now.getTime- 86400000L)
 
 
@@ -342,6 +342,7 @@ object Repeated_content_recommendation_moreday {
 
       val repeated_rate= fenmu / fenzi.toDouble
       val result=List((yesterday,repeated_rate))
+      println(result)
       val df_result = sc.createDataFrame(result)
 
       GmeiConfig.writeToJDBCTable(df_result, table = "Repeated_content_recommendation_moreday", SaveMode.Append)
@@ -351,10 +352,7 @@ object Repeated_content_recommendation_moreday {
 //      GmeiConfig.writeToJDBCTable(df, table = "Repeated_evaluation_indicator_moreday", SaveMode.Append)
 
     }
-
-
   }
-
 }
 
 
@@ -640,3 +638,231 @@ object GetHiveSearchData {
 
   }
 
+
+
+
+object find_reason {
+
+  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 ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure_precise")
+
+//      val stat_date = GmeiConfig.getMinusNDate(1)
+      val stat_date=param.date
+      val partition_date = stat_date.replace("-","")
+      //机构id
+      val blacklist = sc.sql(
+        s"""
+           |select device_id from blacklist
+         """.stripMargin
+      )
+      blacklist.createOrReplaceTempView("blacklist")
+
+      val agency_id = sc.sql(
+        s"""
+           |SELECT DISTINCT(cl_id) as device_id
+           |FROM online.ml_hospital_spam_pv_day
+           |WHERE partition_date >= '20180402'
+           |AND partition_date <= '${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 <= '${partition_date}'
+           |AND pv_ratio >= 0.95
+         """.stripMargin
+      )
+      agency_id.show()
+      agency_id.createOrReplaceTempView("agency_id")
+      //每日新用户
+      val device_id_newUser = sc.sql(
+        s"""
+           |select distinct(os.device_id) as device_id
+           |from online.ml_device_day_active_status os left join blacklist
+           |on os.device_id = blacklist.device_id
+           |where os.active_type != '4'
+           |and os.first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
+           |    ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
+           |    ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
+           |    ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
+           |    ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
+           |    ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
+           |    ,'promotion_shike','promotion_julang_jl03','','unknown')
+           |and os.partition_date ='${partition_date}'
+           |and blacklist.device_id is null
+         """.stripMargin
+      )
+      device_id_newUser.show()
+      device_id_newUser.createOrReplaceTempView("device_id_new")
+
+      //每日老用户
+      val device_id_oldUser = sc.sql(
+        s"""
+           |select distinct(os.device_id) as device_id
+           |from online.ml_device_day_active_status os left join blacklist
+           |on os.device_id=blacklist.device_id
+           |where os.active_type = '4'
+           |and os.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 os.partition_date ='${partition_date}'
+           |and blacklist.device_id is null
+         """.stripMargin
+      )
+      device_id_oldUser.show()
+      device_id_oldUser.createOrReplaceTempView("device_id_old")
+
+
+
+      val all_clk = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date,ov.cl_id as device_id
+           |from online.tl_hdfs_maidian_view ov left join agency_id
+           |on ov.cl_id = agency_id.device_id
+           |where ov.action = 'on_click_diary_card'
+           |and ov.cl_id != "NULL"
+           |and ov.partition_date='${partition_date}'
+           |and agency_id.device_id is  null
+       """.stripMargin
+      )
+      all_clk.show()
+      all_clk.createOrReplaceTempView("all_clk_diary_card")
+
+      //1.当天老用户中的点击用户数
+      val old_clk_count = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date,count(oc.device_id) as old_clk_count
+           |from all_clk_diary_card oc inner join device_id_old
+           |on oc.device_id = device_id_old.device_id
+           |group by stat_date
+       """.stripMargin
+      )
+      old_clk_count.show()
+      //1.1有点击的老用户
+      val old_clk_device = sc.sql(
+        s"""
+           |select distinct(oc.device_id) as device_id
+           |from all_clk_diary_card oc inner join device_id_old
+           |on oc.device_id = device_id_old.device_id
+       """.stripMargin
+      )
+      old_clk_device.createOrReplaceTempView("old_clk_device")
+
+
+
+      //2.当天新用户中的点击用户数
+      val new_clk_count = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date,count(oc.device_id) as new_clk_count
+           |from all_clk_diary_card oc inner join device_id_new
+           |on oc.device_id = device_id_new.device_id
+           |group by stat_date
+       """.stripMargin
+      )
+//2.1 有点击的新用户
+      val new_clk_device = sc.sql(
+        s"""
+           |select distinct(oc.device_id) as device_id
+           |from all_clk_diary_card oc inner join device_id_new
+           |on oc.device_id = device_id_new.device_id
+       """.stripMargin
+      )
+      new_clk_device.createOrReplaceTempView("new_clk_device")
+
+
+      //3.当天老用户数
+
+      val old_count = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date,count(distinct(dio.device_id)) as old_count
+           |from device_id_old dio inner join agency_id
+           |on dio.device_id = agency_id.device_id
+       """.stripMargin
+      )
+
+      //4.当天新用户数
+      val new_count = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date,count(distinct(din.device_id)) as new_count
+           |from device_id_new din inner join agency_id
+           |on din.device_id = agency_id.device_id
+       """.stripMargin
+      )
+
+      //5.有点击老用户的曝光数
+      val exp_clkold_count = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date,count(dp.device_id) as imp_clkold_count
+           |from data_feed_exposure_precise dp inner join old_clk_device
+           |on dp.device_id = old_clk_device.device_id
+           |where stat_date='${stat_date}'
+           |group by stat_date
+       """.stripMargin
+      )
+
+      //6.有点击新用户的曝光数
+      val exp_clknew_count = sc.sql(
+        s"""
+           |select '${stat_date}' as stat_date,count(dp.device_id) as imp_clknew_count
+           |from data_feed_exposure_precise dp inner join new_clk_device
+           |on dp.device_id = new_clk_device.device_id
+           |where stat_date='${stat_date}'
+           |group by stat_date
+       """.stripMargin
+      )
+
+      val result = old_clk_count.join(new_clk_count,"stat_date")
+        .join(old_count,"stat_date")
+        .join(new_count,"stat_date")
+        .join(exp_clkold_count,"stat_date")
+        .join(exp_clknew_count,"stat_date")
+
+      GmeiConfig.writeToJDBCTable(result, "device_clk_imp_reason", SaveMode.Append)
+
+
+    }
+
+  }
+
+
+}

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

@@ -76,22 +76,24 @@ object testt {
            |AND pv_ratio >= 0.95
          """.stripMargin
       )
-      agency_id.show()
+//      agency_id.show()
       agency_id.createOrReplaceTempView("agency_id")
 //每日新用户
       val device_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'
+           |select distinct(os.device_id) as device_id
+           |from online.ml_device_day_active_status os left join blacklist
+           |on os.device_id=blacklist.device_id
+           |where os.active_type != '4'
+           |and os.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 partition_date ='${partition_date}'
+           |and os.partition_date ='${partition_date}'
+           |and blacklist.device_id is null
          """.stripMargin
       )
       device_id_newUser.show()
@@ -103,19 +105,19 @@ object testt {
            |select distinct(os.device_id) as device_id
            |from online.ml_device_day_active_status os left join blacklist
            |on os.device_id=blacklist.device_id
-           |where active_type = '4'
-           |and first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
+           |where os.active_type = '4'
+           |and os.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 partition_date ='${partition_date}'
+           |and os.partition_date ='${partition_date}'
            |and blacklist.device_id is null
          """.stripMargin
       )
-      device_id_oldUser.show()
+//      device_id_oldUser.show()
       device_id_oldUser.createOrReplaceTempView("device_id_old")