广告分桶

src/main/scala/com/aliyun/odps/spark/examples/makedata_ad/makedata_32_bucket_20240622.scala

@@ -47,9 +47,14 @@ object makedata_32_bucket_20240622 {
     val bucketNum = param.getOrElse("bucketNum", "100").toInt
 
     val data = sc.textFile(readPath)
+    println("问题数据数量：" + data.filter(r=>r.split("\t").length != 3).count())
     val data1 = data.map(r => {
       val rList = r.split("\t")
-      val doubles = JSON.parseObject(rList(2)).mapValues(_.toString.toDouble).toMap
+      val jsons = JSON.parseObject(rList(2))
+      val doubles = scala.collection.mutable.Map[String, Double]()
+      jsons.foreach(r =>{
+        doubles.put(r._1, jsons.getDoubleValue(r._1))
+      })
       doubles
     }).sample(false, sampleRate ).repartition(20)