spark入门.txt

//1 sqlContext基础应用

//RDD演示
val sqlContext= new org.apache.spark.sql.SQLContext(sc)
import sqlContext.createSchemaRDD  

case class Person(name:String,age:Int)
     val rddpeople=sc.textFile("/sparksql/people.txt").map(_.split(",")).map(p=>Person(p(0),p(1).trim.toInt))
     rddpeople.registerTempTable("rddTable")
     sqlContext.sql("SELECT name FROM rddTable WHERE age >= 13 AND age <= 19").map(t => "Name: " + t(0)).collect().foreach(println)



//parquet演示
rddpeople.saveAsParquetFile("/sparksql/people.parquet")
val parquetpeople = sqlContext.parquetFile("/sparksql/people.parquet")
parquetpeople.registerTempTable("parquetTable")
sqlContext.sql("SELECT name FROM parquetTable WHERE age >= 25").map(t => "Name: " + t(0)).collect().foreach(println)  



//json演示
val jsonpeople = sqlContext.jsonFile("/sparksql/people.json")
jsonpeople.registerTempTable("jsonTable")
sqlContext.sql("SELECT name FROM jsonTable WHERE age >= 25").map(t => "Name: " + t(0)).collect().foreach(println)