统计推荐日记重复指标

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

@@ -163,4 +163,81 @@ object temp_count {
 
   }
 
+}
+
+
+
+
+object Repeated_content_recommendation {
+
+  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 ${defaultParams.env}"
+    )
+  }
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "diary_video")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "blacklist")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "data_feed_exposure")
+      ti.tidbMapTable(dbName = "jerry_prod", tableName = "merge_queue_table")
+
+
+      //      val stat_date = GmeiConfig.getMinusNDate(1)
+      val stat_date = param.date
+      val partition_date = stat_date.replace("-","")
+
+
+      val exp_diary = sc.sql(
+        s"""
+           |select concat_ws(|,device_id,cid_id)
+           |from data_feed_exposure
+           |where cid_type = 'diary'
+           |and device_id not in (select device_id from blacklist)
+           |and stat_date ='${stat_date}'
+         """.stripMargin
+      )
+      exp_diary.show()
+      val get_result =exp_diary.rdd.map((_, 1)).reduceByKey(_ + _)
+              .sortBy(_._2,false)
+
+      val temp=get_result.collect()
+            for (i <- 0 until temp.length ) {
+              println(temp(i))
+            }
+
+
+    }
+
+
+  }
+
 }
\ No newline at end of file