smart_rank 相关的统计指标

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

@@ -526,3 +526,119 @@ object meigou_xiaofei_renshu {
 
 }
 
+
+
+
+object smart_rank_count {
+
+  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 meigou_price = sc.sql(
+              s"""
+                 |select *
+                 |from online.tl_hdfs_maidian_view
+                 |where action = "page_view"
+                 |and params['page_name']="diary_detail"
+                 |and partition_date ='20181201'
+                 |LIMIT 10
+             """.stripMargin
+            )
+            meigou_price.show(80)
+
+      //      GmeiConfig.writeToJDBCTable(meigou_price, "meigou_price", SaveMode.Overwrite)
+
+    }
+
+
+  }
+
+}
+
+
+
+
+
+
+