我的大数据之旅-Spark SQL DataFrame常用操作

package com.fengling.sql

import org.apache.spark.SparkConf
import org.apache.spark.sql.{DataFrame, SparkSession}
import org.slf4j.LoggerFactory

case class People(name: String, age: Int)

/**
  * @author fengchengliang@126.com
  * @date 2019-10-17
  */
object SparkSQLDemo {
  val logger = LoggerFactory.getLogger(SparkSQLDemo.getClass)

  def main(args: Array[String]): Unit = {
    val config = Map(
      "spark.cores" -> "local[*]"
    )
    val sparkConf = new SparkConf().setMaster(config("spark.cores")).setAppName("Spark SQL basic example")
    // 创建SparkContext并设置AppName
    val spark = SparkSession.builder()
      .config(sparkConf)
      .getOrCreate()

    // For implicit conversions like converting RDDs to DataFrames
    import spark.implicits._

    val rdd = spark.sparkContext.parallelize(List(People("张三",12),People("李四",18),People("王五",2