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

change predict

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

@@ -182,3 +182,118 @@ object temp_analysis {
   }
 
 }
+
+
+
+
+
+
+object ARPU_COM {
+
+  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 ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_test", tableName = "bl_device_list")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "merge_queue_table")
+
+
+      import sc.implicits._
+      val stat_date = GmeiConfig.getMinusNDate(1)
+      //println(param.date)
+      val partition_date = stat_date.replace("-","")
+
+      val agency_id = sc.sql(
+        s"""
+           |SELECT DISTINCT(cl_id) as device_id
+           |FROM online.ml_hospital_spam_pv_day
+           |WHERE partition_date >= '20180402'
+           |AND partition_date <= '${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.createOrReplaceTempView("agency_id")
+
+      val blacklist_id = sc.sql(
+        s"""
+           |SELECT device_id
+           |from blacklist
+         """.stripMargin
+      )
+      blacklist_id.createOrReplaceTempView("blacklist_id")
+
+      val final_id = sc.sql(
+        s"""
+           |select device_id
+           |from agency_id
+           |UNION ALL
+           |select device_id
+           |from blacklist_id
+         """.stripMargin
+      )
+      final_id.createOrReplaceTempView("final_id")
+
+
+      val diary_clk_all = sc.sql(
+        s"""
+           |select count(md.payment) as pay_all,count(distinct(md.device_id)) as pay_people,count(md.payment)/count(distinct(md.device_id))
+           |from online.ml_meigou_order_detail md left join final_id
+           |on md.device_id = final_id.device_id
+           |where md.status='2'
+           |and final_id.device_id is  null
+           |and md.partition_date = '20181218'
+           |and  md.pay_time  is  not  null
+           |and  md.pay_time  >=  '2018-01-01'
+       """.stripMargin
+      )
+      diary_clk_all.show(80)
+
+
+
+    }
+
+
+  }
+
+}
+

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

@@ -66,13 +66,13 @@ object testt {
            |SELECT DISTINCT(cl_id) as device_id
            |FROM online.ml_hospital_spam_pv_day
            |WHERE partition_date >= '20180402'
-           |AND partition_date <= '20181203'
+           |AND partition_date <= '${partition_date}'
            |AND pv_ratio >= 0.95
            |UNION ALL
            |SELECT DISTINCT(cl_id) as device_id
            |FROM online.ml_hospital_spam_pv_month
            |WHERE partition_date >= '20171101'
-           |AND partition_date <= '20181203'
+           |AND partition_date <= '${partition_date}'
            |AND pv_ratio >= 0.95
          """.stripMargin
       )