spark 如何操作两个文件呢?
看下面样例:
创建了两个临时表,而后在编写语句。
class vistorcount extends Serializable{
//the defination please put here,otherwise it will compile error.
case class person(name:String,age:Int)
case class personscore(name:String,score:Int)
//case class mobiledata(mobile:String,longtitude:String,latitude:String,status:Int,createtime:String)
case class mobiledata(mobile:String,longtitude:String,latitude:String)
case class mobilecity(mobilerange:String,city:String)
def getpeople(): Unit = {
val conf = new SparkConf().setAppName("traveldata").setMaster("local[*]")
val sc = new SparkContext(conf)
val sqlContext = new SQLContext(sc)
import sqlContext.implicits._
val df = sc.textFile("c://traveldata//people.txt", 1)
.map(_.split(","))
.map(p=>person(p(0),p(1).trim.toInt))
.toDF()
df.registerTempTable("people")
//cacheTable("people")
val ps = sc.textFile("c://traveldata//peoplescore.txt", 1).map(_.split(",")).map(p=>personscore(p(0),p(1).trim.toInt)).toDF()
ps.registerTempTable("personscore")
val resultDF = sqlContext.sql("select people.name,people.age,personscore.score from people,personscore where people.name=personscore.name");
//resultDF.show()
resultDF.collect().foreach(println)
sc.stop()
}
}