spark sql

package com.spark.sql

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.types.StructField
import org.apache.spark.sql.types.StringType
import org.apache.spark.sql.Row

object SpecifySchema {
  def main(args: Array[String]): Unit = {
     val conf = new SparkConf()
      .setAppName("ReflectionSchema")
      .setMaster("local")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)
     
     // Create an RDD
val people = sc.textFile("C:\\Users\\xiaoming.liang\\Desktop\\people.txt")
      val schemaString = "name age"
      
 val schema =  StructType(schemaString.split(" ").map { fieldName  => StructField(fieldName, StringType, true) })
     
   // val rowRDD = people.map { x => x.split(",") } 
      val rowRDD = people.map(_.split(",")).map(p => Row(p(0),p(1).trim))
      
// Apply the schema to the RDD.
   val peopleDataFrame=   sqlContext.createDataFrame(rowRDD, schema)
      
     // Register the DataFrames as a table.
       peopleDataFrame.registerTempTable("people")
     
      // SQL statements can be run by using the sql methods provided by sqlContext.
      val results = sqlContext.sql("SELECT name FROM people") 
      
      // The results of SQL queries are DataFrames and support all the normal RDD operations.
      // The columns of a row in the result can be accessed by field index or by field name.
      results.map(t => "Name: " + t(0)).collect().foreach(println)
  }
}


people.txt

xiaoming,23
xiaohong,21
zhangsan,20
lisi,10
wangwu,30


  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值