Commit 7e8d57c2 authored by 高雅喆's avatar 高雅喆

add diary count from 300 to 500

parent d527ef65
......@@ -283,7 +283,7 @@ object EsmmPredData {
case (device_city, cid_data) =>
val device_id = Try(device_city.split(",")(0)).getOrElse("")
val city_id = Try(device_city.split(",")(1)).getOrElse("")
val cids = Try(cid_data.toSeq.map(_.getAs[String]("merge_queue").split(",")).flatMap(_.zipWithIndex).sortBy(_._2).map(_._1).distinct.take(300).mkString(",")).getOrElse("")
val cids = Try(cid_data.toSeq.map(_.getAs[String]("merge_queue").split(",")).flatMap(_.zipWithIndex).sortBy(_._2).map(_._1).distinct.take(500).mkString(",")).getOrElse("")
(device_id,city_id ,s"$cids")
}.filter(_._3!="").toDF("device_id","city_id","merge_queue")
raw_data1.createOrReplaceTempView("raw_data1")
......@@ -312,7 +312,7 @@ object EsmmPredData {
val native_data1 = sc.sql(
s"""
|select device_id,city_id as ucity_id,
|explode(split(split(native_queue, concat(',',split(native_queue,',')[300]))[0],',')) as cid_id
|explode(split(split(native_queue, concat(',',split(native_queue,',')[500]))[0],',')) as cid_id
|from native_data
""".stripMargin
).withColumn("label",lit(0))
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment