新用户去掉用户黑名单

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

@@ -640,3 +640,155 @@ 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 ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+
+      val stat_date = GmeiConfig.getMinusNDate(1)
+      //      val stat_date=param.date
+      val partition_date = stat_date.replace("-","")
+      //机构id
+      val blacklist = sc.sql(
+        s"""
+           |select device_id from blacklist
+         """.stripMargin
+      )
+      blacklist.createOrReplaceTempView("blacklist")
+
+      val agency_id = sc.sql(
+        s"""
+           |SELECT DISTINCT(cl_id) as device_id
+           |FROM online.ml_hospital_spam_pv_day
+           |WHERE partition_date >= '20180402'
+           |AND partition_date <= '${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 <= '${partition_date}'
+           |AND pv_ratio >= 0.95
+         """.stripMargin
+      )
+      agency_id.show()
+      agency_id.createOrReplaceTempView("agency_id")
+      //每日新用户
+      val device_id_newUser = sc.sql(
+        s"""
+           |select distinct(os.device_id) as device_id
+           |from online.ml_device_day_active_status os left join blacklist
+           |where os.active_type != '4'
+           |and os.first_channel_source_type not in ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
+           |    ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
+           |    ,'js-az1','js-az2','js-az3','js-az4','js-az5','jfq-az1','jfq-az2','jfq-az3','jfq-az4','jfq-az5','toufang1'
+           |    ,'toufang2','toufang3','toufang4','toufang5','toufang6','TF-toufang1','TF-toufang2','TF-toufang3','TF-toufang4'
+           |    ,'TF-toufang5','tf-toufang1','tf-toufang2','tf-toufang3','tf-toufang4','tf-toufang5','benzhan','promotion_aso100'
+           |    ,'promotion_qianka','promotion_xiaoyu','promotion_dianru','promotion_malioaso','promotion_malioaso-shequ'
+           |    ,'promotion_shike','promotion_julang_jl03','','unknown')
+           |and os.partition_date ='${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 ='${partition_date}'
+           |and blacklist.device_id is null
+         """.stripMargin
+      )
+      device_id_oldUser.show()
+      device_id_oldUser.createOrReplaceTempView("device_id_old")
+
+
+      //日记本转化美购
+      //1.日记本到美购转化数
+      val diary_meigou_temp = sc.sql(
+        s"""
+           |select ou.cl_id as device_id
+           |from online.bl_hdfs_page_view_updates ou left join agency_id
+           |on ou.cl_id = agency_id.device_id
+           |where ou.partition_date = '${partition_date}'
+           |and ou.page_name='welfare_detail'
+           |and ou.referrer='diary_detail'
+           |and agency_id.device_id is  null
+         """.stripMargin
+      )
+      diary_meigou_temp.createOrReplaceTempView("diary_meigou_temp")
+
+
+
+
+
+      val result = diary_meigou_newUser.join(diary_meigou_oldUser,"stat_date")
+        .join(diary_clk_newUser,"stat_date")
+        .join(diary_clk_oldUser,"stat_date")
+        .join(diary_exp_newUser,"stat_date")
+        .join(diary_exp_oldUser,"stat_date")
+        .join(search_newUser,"stat_date")
+        .join(search_oldUser,"stat_date")
+        .join(log_newUser,"stat_date")
+        .join(log_oldUser,"stat_date")
+
+      GmeiConfig.writeToJDBCTable(result, "diary_meigou_crv", SaveMode.Append)
+
+
+    }
+
+  }
+
+
+}

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

@@ -76,7 +76,7 @@ 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(
@@ -116,7 +116,7 @@ object testt {
            |and blacklist.device_id is null
          """.stripMargin
       )
-      device_id_oldUser.show()
+//      device_id_oldUser.show()
       device_id_oldUser.createOrReplaceTempView("device_id_old")