简单案例

import org.apache.spark.sql.SparkSession
import org.junit.Test

case class Person(id:Int,name:String,sex:String,age:Int)
class DataSetCreate {

  val spark = SparkSession
    .builder()
    .appName("test")
    .master("local[4]")
    .getOrCreate()
  import spark.implicits._

  @Test
  def createData():Unit={
    val list = List(Person(1,"zhangsan","man",10),
      Person(2,"zhang2","woman",66),
      Person(3,"zhang3","man",70),
      Person(4,"zhang4","man",22))

    val df = list.toDF()
    //TODO 1.将dataFrame/dataSet数据集注册成表
    df.createOrReplaceTempView("person")
    spark.sql(
      """
        |select
        |name,age
        |from person
        |where age >=30
        |""".stripMargin).show()
  }

}

写个小案例

• 获取每个单词的个数

数据源

hello java
spark hadoop flume kafka
hbase kafka flume hadoop

Lateral View explode(split(value," "))是列转行

import org.apache.spark.sql.SparkSession
import org.junit.Test

class DataSetCreate {

  val spark = SparkSession
    .builder()
    .appName("test")
    .master("local[4]")
    .getOrCreate()
  import spark.implicits._

  @Test
  def createData():Unit={
    val ds = spark.read.textFile("src/main/resources/wc.txt")
    ds.createOrReplaceTempView("wordCount")

    spark.sql(
      """
        |select
        | wc,
        | count(1)
        |from wordCount Lateral View explode(split(value," ")) as wc
        |group by wc;
        |""".stripMargin).show()
  }
}