spark下rdd和dataframe以及sqlcontext之間相互轉換

直接看代碼

import org.apache.spark.sql.{DataFrame, SQLContext}
import org.apache.spark.{SparkConf, SparkContext}

/**
  * wo xi huan xie dai ma
  * Created by wangtuntun on 16-5-7.
  */
object clean {

  def main(args: Array[String]) {

    //設置環境
    val conf=new SparkConf().setAppName("tianchi").setMaster("local")
    val sc=new SparkContext(conf)
    val sqc=new SQLContext(sc)

    case class user_pay_class(shop_id:String,user_id:String,DS:String)//註冊一個類

    val user_pay_raw=sc.textFile("/home/wangtuntun/user_pay.txt")
    val user_pay_split=user_pay_raw.map(_.split(","))
    val user_transform =user_pay_split.map{ x=>    //數據轉換
      val userid=x(0)
      val shop_id=x(1)
      val ts=x(2)
      val ts_split=ts.split(" ")
      val year_month_day=ts_split(0).split("-")
      val year=year_month_day(0)
      val month=year_month_day(1)
      val day=year_month_day(2)
//      (shop_id,userid,year,month,day)
      (shop_id,userid,ts_split(0))
    }
    val df=sqc.createDataFrame(user_transform)  // 生成一個dataframe
    val df_name_colums=df.toDF("shop_id","userid","DS")  //給df的每個列取名字
    df_name_colums.registerTempTable("user_pay_table")     //註冊臨時表
    val sql="select shop_id,count(userid),DS from user_pay_table group by shop_id,DS order by shop_id desc,DS"
    val rs: DataFrame =sqc.sql(sql)
    rs.foreach(x=>println(x))
//    user_transform.saveAsTextFile("/home/wangtuntun/test_file4.txt")
    val rs_rdd=rs.map( x=>( x(0),x(1),x(2) ) )         //rs轉爲rdd
    rs_rdd.saveAsTextFile("/home/wangtuntun/test_file5.txt")
    sc.stop();

  }


}