sparksql中三种方式创建DataFrame
0.准备数据person.txt
1 zhangsan 20
2 lisi 29
3 wangwu 25
4 zhaoliu 30
5 xiaoqi 35
6 kobe 40
1.使用样例类+反射创建DataFrame
package com.xyz.sparksql
import org.apache.spark.rdd.RDD
import org.apache.spark.{
SparkConf, SparkContext}
import org.apache.spark.sql.{
DataFrame, SparkSession}
object DataFrameDemo1 {
/*
演示创建DataFrame-使用RDD转换--Schema使用样例类+反射添加的
*/
def main(args: Array[String]): Unit = {
//1.创建SparkSession,获取SparkContext
val conf: SparkConf = new SparkConf().setAppName("DataFrameDemo1").setMaster("local[*]")
val spark: SparkSession = SparkSession.builder().config(conf).getOrCreate()
val sc: SparkContext = spark.sparkContext
//指定日志级别
sc.setLogLevel("WARN")
//2.读取文件
val fileRDD: RDD[String] = sc.textFile("F:\\data\\person.txt")
//3.处理文件数据
val linesRDD: RDD[Array[String]] = fileRDD.map(url =>url.split(