Parcourir la source

去掉重复数据

jch il y a 4 jours
Parent
commit
36c48b901e

+ 1 - 2
src/main/scala/com/aliyun/odps/spark/examples/makedata_ad/v20240718/makedata_ad_33_bucketDataFromOriginToHive_20250522.scala

@@ -697,9 +697,8 @@ object makedata_ad_33_bucketDataFromOriginToHive_20250522 {
         .map(featMap => {
           val apptype = featMap.getOrElse("apptype", "")
           val mid = featMap.getOrElse("mid", "")
-          val cid = featMap.getOrElse("cid", "")
           val pqtid = featMap.getOrElse("pqtid", "")
-          val uniqKey = (apptype, mid, cid, pqtid).productIterator.mkString(",")
+          val uniqKey = (apptype, mid, pqtid).productIterator.mkString(",")
           (uniqKey, featMap)
         })
         .reduceByKey((a, b) => a)