sparksql demo III (dataFrame方式)

package com.ws.sparksql
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.types._
import org.apache.spark.sql.{DataFrame, Dataset, Row, SQLContext}
import org.apache.spark.{SparkConf, SparkContext}
/**
  * spark sql版本 1.1x
  * spark sql 第3个demo
  */
object SparkSqlDemo3 {

  def main(args: Array[String]): Unit = {

    val conf = new SparkConf().setAppName("SparkSqlDemo3").setMaster("local[2]")

    val sc = new SparkContext(conf)
    //创建一个sparksql实例
    val sQLContext = new SQLContext(sc)

    val dataRdd: RDD[String] = sc.textFile("hdfs://hadoop-01:9000/student")

    val rowRdd: RDD[Row] = dataRdd.map(line => {

      val strArr: Array[String] = line.split(",")
      val id = strArr(0).toLong
      val name = strArr(1)
      val age = strArr(2).toInt
      val score = strArr(3).toInt
      Row(id, name, age, score)
    })


    val schema = StructType(List(
      //参数1：字段名， 参数2：字段类型，参数3:是否允许null
      StructField("id",LongType,false),
      StructField("name",StringType,false),
      StructField("age",IntegerType,false),
      StructField("score",IntegerType,false)
    ))

    val sdf: DataFrame = sQLContext.createDataFrame(rowRdd,schema)

    //使用dataFrame方式查询数据
    val column: DataFrame = sdf.select("name","age","score")
    //排序
    import sQLContext.implicits._

    val result: Dataset[Row] = column.sort($"score" desc , $"age" asc)

    //触发Action操作，展示结果
    result.show()
    sc.stop()
  }
}

结果 ：

+----+---+-----+
|name|age|score|
+----+---+-----+
|  张三| 18|  150|
|  李四| 19|  150|
|  王五| 20|   98|
|  赵六| 17|   88|
+----+---+-----+